Akshat Kumar

Gerald Woo, Chenghao Liu, Doyen Sahoo et al.

Deep learning has been actively applied to time series forecasting, leading to a deluge of new methods, belonging to the class of historical-value models. Yet, despite the attractive properties of time-index models, such as being able to model the continuous nature of underlying time series dynamics, little attention has been given to them. Indeed, while naive deep time-index models are far more expressive than the manually predefined function representations of classical time-index models, they are inadequate for forecasting, being unable to generalize to unseen time steps due to the lack of inductive bias. In this paper, we propose DeepTime, a meta-optimization framework to learn deep time-index models which overcome these limitations, yielding an efficient and accurate forecasting model. Extensive experiments on real world datasets in the long sequence time-series forecasting setting demonstrate that our approach achieves competitive results with state-of-the-art methods, and is highly efficient. Code is available at https://github.com/salesforce/DeepTime.

Gerald Woo, Chenghao Liu, Akshat Kumar et al.

Time series has been left behind in the era of pre-training and transfer learning. While research in the fields of natural language processing and computer vision are enjoying progressively larger datasets to train massive models, the most popular time series datasets consist of only tens of thousands of time steps, limiting our ability to study the effectiveness of pre-training and scaling. Recent studies have also cast doubt on the need for expressive models and scale. To alleviate these issues, we introduce three large-scale time series forecasting datasets from the cloud operations (CloudOps) domain, the largest having billions of observations, enabling further study into pre-training and scaling of time series models. We build the empirical groundwork for studying pre-training and scaling of time series models and pave the way for future research by identifying a promising candidate architecture. We show that it is a strong zero-shot baseline and benefits from further scaling, both in model and dataset size. Accompanying these datasets and results is a suite of comprehensive benchmark results comparing classical and deep learning baselines to our pre-trained method - achieving a 27% reduction in error on the largest dataset. Code and datasets can be found https://github.com/SalesforceAIResearch/pretrain-time-series-cloudops.

Siow Meng Low, Akshat Kumar, Scott Sanner

Recent advances in deep learning have enabled optimization of deep reactive policies (DRPs) for continuous MDP planning by encoding a parametric policy as a deep neural network and exploiting automatic differentiation in an end-to-end model-based gradient descent framework. This approach has proven effective for optimizing DRPs in nonlinear continuous MDPs, but it requires a large number of sampled trajectories to learn effectively and can suffer from high variance in solution quality. In this work, we revisit the overall model-based DRP objective and instead take a minorization-maximization perspective to iteratively optimize the DRP w.r.t. a locally tight lower-bounded objective. This novel formulation of DRP learning as iterative lower bound optimization (ILBO) is particularly appealing because (i) each step is structurally easier to optimize than the overall objective, (ii) it guarantees a monotonically improving objective under certain theoretical conditions, and (iii) it reuses samples between iterations thus lowering sample complexity. Empirical evaluation confirms that ILBO is significantly more sample-efficient than the state-of-the-art DRP planner and consistently produces better solution quality with lower variance. We additionally demonstrate that ILBO generalizes well to new problem instances (i.e., different initial states) without requiring retraining.

Siow Meng Low, Akshat Kumar, Scott Sanner

In safe MDP planning, a cost function based on the current state and action is often used to specify safety aspects. In the real world, often the state representation used may lack sufficient fidelity to specify such safety constraints. Operating based on an incomplete model can often produce unintended negative side effects (NSEs). To address these challenges, first, we associate safety signals with state-action trajectories (rather than just an immediate state-action). This makes our safety model highly general. We also assume categorical safety labels are given for different trajectories, rather than a numerical cost function, which is harder to specify by the problem designer. We then employ a supervised learning model to learn such non-Markovian safety patterns. Second, we develop a Lagrange multiplier method, which incorporates the safety model and the underlying MDP model in a single computation graph to facilitate agent learning of safe behaviors. Finally, our empirical results on a variety of discrete and continuous domains show that this approach can satisfy complex non-Markovian safety constraints while optimizing an agent's total returns, is highly scalable, and is also better than the previous best approach for Markovian NSEs.

Gerald Woo, Chenghao Liu, Akshat Kumar et al.

Deep learning for time series forecasting has traditionally operated within a one-model-per-dataset framework, limiting its potential to leverage the game-changing impact of large pre-trained models. The concept of universal forecasting, emerging from pre-training on a vast collection of time series datasets, envisions a single Large Time Series Model capable of addressing diverse downstream forecasting tasks. However, constructing such a model poses unique challenges specific to time series data: i) cross-frequency learning, ii) accommodating an arbitrary number of variates for multivariate time series, and iii) addressing the varying distributional properties inherent in large-scale data. To address these challenges, we present novel enhancements to the conventional time series Transformer architecture, resulting in our proposed Masked Encoder-based Universal Time Series Forecasting Transformer (Moirai). Trained on our newly introduced Large-scale Open Time Series Archive (LOTSA) featuring over 27B observations across nine domains, Moirai achieves competitive or superior performance as a zero-shot forecaster when compared to full-shot models. Code, data, and model weights can be found at https://github.com/SalesforceAIResearch/uni2ts.

Mikhail Kazdagli, Mohit Tiwari, Akshat Kumar

Modern software systems rely on mining insights from business sensitive data stored in public clouds. A data breach usually incurs significant (monetary) loss for a commercial organization. Conceptually, cloud security heavily relies on Identity Access Management (IAM) policies that IT admins need to properly configure and periodically update. Security negligence and human errors often lead to misconfiguring IAM policies which may open a backdoor for attackers. To address these challenges, first, we develop a novel framework that encodes generating optimal IAM policies using constraint programming (CP). We identify reducing dark permissions of cloud users as an optimality criterion, which intuitively implies minimizing unnecessary datastore access permissions. Second, to make IAM policies interpretable, we use graph representation learning applied to historical access patterns of users to augment our CP model with similarity constraints: similar users should be grouped together and share common IAM policies. Third, we describe multiple attack models and show that our optimized IAM policies significantly reduce the impact of security attacks using real data from 8 commercial organizations, and synthetic instances.

Akshat Kumar, Mohan Sarovar

Experimental sciences have come to depend heavily on our ability to organize and interpret high-dimensional datasets. Natural laws, conservation principles, and inter-dependencies among observed variables yield geometric structure, with fewer degrees of freedom, on the dataset. We introduce the frameworks of semiclassical and microlocal analysis to data analysis and develop a novel, yet natural uncertainty principle for extracting fine-scale features of this geometric structure in data, crucially dependent on data-driven approximations to quantum mechanical processes underlying geometric optics. This leads to the first tractable algorithm for approximation of wave dynamics and geodesics on data manifolds with rigorous probabilistic convergence rates under the manifold hypothesis. We demonstrate our algorithm on real-world datasets, including an analysis of population mobility information during the COVID-19 pandemic to achieve four-fold improvement in dimensionality reduction over existing state-of-the-art and reveal anomalous behavior exhibited by less than 1.2% of the entire dataset. Our work initiates the study of data-driven quantum dynamics for analyzing datasets, and we outline several future directions for research.

Ze Gong, Pradeep Varakantham, Akshat Kumar

Offline Preference-based Reinforcement Learning (PbRL) learns rewards and policies aligned with human preferences without the need for extensive reward engineering and direct interaction with human annotators. However, ensuring safety remains a critical challenge across many domains and tasks. Previous works on safe RL from human feedback (RLHF) first learn reward and cost models from offline data, then use constrained RL to optimize a safe policy. While such an approach works in the contextual bandits settings (LLMs), in long horizon continuous control tasks, errors in rewards and costs accumulate, leading to impairment in performance when used with constrained RL methods. To address these challenges, (a) instead of indirectly learning policies (from rewards and costs), we introduce a framework that learns a policy directly based on pairwise preferences regarding the agent's behavior in terms of rewards, as well as binary labels indicating the safety of trajectory segments; (b) we propose \textsc{PreSa} (Preference and Safety Alignment), a method that combines preference learning module with safety alignment in a constrained optimization problem. This optimization problem is solved within a Lagrangian paradigm that directly learns reward-maximizing safe policy \textit{without explicitly learning reward and cost models}, avoiding the need for constrained RL; (c) we evaluate our approach on continuous control tasks with both synthetic and real human feedback. Empirically, our method successfully learns safe policies with high rewards, outperforming state-of-the-art baselines, and offline safe RL approaches with ground-truth reward and cost.

Megha Bose, Praveen Paruchuri, Akshat Kumar

Moving Target Defense (MTD) has emerged as a proactive and dynamic framework to counteract evolving cyber threats. Traditional MTD approaches often rely on assumptions about the attackers knowledge and behavior. However, real-world scenarios are inherently more complex, with adaptive attackers and limited prior knowledge of their payoffs and intentions. This paper introduces a novel approach to MTD using a Markov Decision Process (MDP) model that does not rely on predefined attacker payoffs. Our framework integrates the attackers real-time responses into the defenders MDP using a dynamic Bayesian Network. By employing a factored MDP model, we provide a comprehensive and realistic system representation. We also incorporate incremental updates to an attack response predictor as new data emerges. This ensures an adaptive and robust defense mechanism. Additionally, we consider the costs of switching configurations in MTD, integrating them into the reward structure to balance execution and defense costs. We first highlight the challenges of the problem through a theoretical negative result on regret. However, empirical evaluations demonstrate the frameworks effectiveness in scenarios marked by high uncertainty and dynamically changing attack landscapes.

Gerald Woo, Chenghao Liu, Doyen Sahoo et al.

Deep learning has been actively studied for time series forecasting, and the mainstream paradigm is based on the end-to-end training of neural network architectures, ranging from classical LSTM/RNNs to more recent TCNs and Transformers. Motivated by the recent success of representation learning in computer vision and natural language processing, we argue that a more promising paradigm for time series forecasting, is to first learn disentangled feature representations, followed by a simple regression fine-tuning step -- we justify such a paradigm from a causal perspective. Following this principle, we propose a new time series representation learning framework for time series forecasting named CoST, which applies contrastive learning methods to learn disentangled seasonal-trend representations. CoST comprises both time domain and frequency domain contrastive losses to learn discriminative trend and seasonal representations, respectively. Extensive experiments on real-world datasets show that CoST consistently outperforms the state-of-the-art methods by a considerable margin, achieving a 21.3% improvement in MSE on multivariate benchmarks. It is also robust to various choices of backbone encoders, as well as downstream regressors. Code is available at https://github.com/salesforce/CoST.

Gerald Woo, Chenghao Liu, Doyen Sahoo et al.

Transformers have been actively studied for time-series forecasting in recent years. While often showing promising results in various scenarios, traditional Transformers are not designed to fully exploit the characteristics of time-series data and thus suffer some fundamental limitations, e.g., they generally lack of decomposition capability and interpretability, and are neither effective nor efficient for long-term forecasting. In this paper, we propose ETSFormer, a novel time-series Transformer architecture, which exploits the principle of exponential smoothing in improving Transformers for time-series forecasting. In particular, inspired by the classical exponential smoothing methods in time-series forecasting, we propose the novel exponential smoothing attention (ESA) and frequency attention (FA) to replace the self-attention mechanism in vanilla Transformers, thus improving both accuracy and efficiency. Based on these, we redesign the Transformer architecture with modular decomposition blocks such that it can learn to decompose the time-series data into interpretable time-series components such as level, growth and seasonality. Extensive experiments on various time-series benchmarks validate the efficacy and advantages of the proposed method. Code is available at https://github.com/salesforce/ETSformer.

Janaka Chathuranga Brahmanage, Akshat Kumar

Sequential decision making using Markov Decision Process underpins many realworld applications. Both model-based and model free methods have achieved strong results in these settings. However, real-world tasks must balance reward maximization with safety constraints, often conflicting objectives, that can lead to unstable min/max, adversarial optimization. A promising alternative is safety reachability analysis, which precomputes a forward-invariant safe state, action set, ensuring that an agent starting inside this set remains safe indefinitely. Yet, most reachability based methods address only hard safety constraints, and little work extends reachability to cumulative cost constraints. To address this, first, we define a safetyconditioned reachability set that decouples reward maximization from cumulative safety cost constraints. Second, we show how this set enforces safety constraints without unstable min/max or Lagrangian optimization, yielding a novel offline safe RL algorithm that learns a safe policy from a fixed dataset without environment interaction. Finally, experiments on standard offline safe RL benchmarks, and a real world maritime navigation task demonstrate that our method matches or outperforms state of the art baselines while maintaining safety.

Janaka Chathuranga Brahmanage, Jiajing Ling, Akshat Kumar

Action-constrained reinforcement learning (ACRL) is a popular approach for solving safety-critical and resource-allocation related decision making problems. A major challenge in ACRL is to ensure agent taking a valid action satisfying constraints in each RL step. Commonly used approach of using a projection layer on top of the policy network requires solving an optimization program which can result in longer training time, slow convergence, and zero gradient problem. To address this, first we use a normalizing flow model to learn an invertible, differentiable mapping between the feasible action space and the support of a simple distribution on a latent variable, such as Gaussian. Second, learning the flow model requires sampling from the feasible action space, which is also challenging. We develop multiple methods, based on Hamiltonian Monte-Carlo and probabilistic sentential decision diagrams for such action sampling for convex and non-convex constraints. Third, we integrate the learned normalizing flow with the DDPG algorithm. By design, a well-trained normalizing flow will transform policy output into a valid action without requiring an optimization solver. Empirically, our approach results in significantly fewer constraint violations (upto an order-of-magnitude for several instances) and is multiple times faster on a variety of continuous control tasks.

Ze Gong, Akshat Kumar, Pradeep Varakantham

Offline safe reinforcement learning (RL) has emerged as a promising approach for learning safe behaviors without engaging in risky online interactions with the environment. Most existing methods in offline safe RL rely on cost constraints at each time step (derived from global cost constraints) and this can result in either overly conservative policies or violation of safety constraints. In this paper, we propose to learn a policy that generates desirable trajectories and avoids undesirable trajectories. To be specific, we first partition the pre-collected dataset of state-action trajectories into desirable and undesirable subsets. Intuitively, the desirable set contains high reward and safe trajectories, and undesirable set contains unsafe trajectories and low-reward safe trajectories. Second, we learn a policy that generates desirable trajectories and avoids undesirable trajectories, where (un)desirability scores are provided by a classifier learnt from the dataset of desirable and undesirable trajectories. This approach bypasses the computational complexity and stability issues of a min-max objective that is employed in existing methods. Theoretically, we also show our approach's strong connections to existing learning paradigms involving human feedback. Finally, we extensively evaluate our method using the DSRL benchmark for offline safe RL. Empirically, our method outperforms competitive baselines, achieving higher rewards and better constraint satisfaction across a wide variety of benchmark tasks.

Siow Meng Low, Akshat Kumar

In safe Reinforcement Learning (RL), safety cost is typically defined as a function dependent on the immediate state and actions. In practice, safety constraints can often be non-Markovian due to the insufficient fidelity of state representation, and safety cost may not be known. We therefore address a general setting where safety labels (e.g., safe or unsafe) are associated with state-action trajectories. Our key contributions are: first, we design a safety model that specifically performs credit assignment to assess contributions of partial state-action trajectories on safety. This safety model is trained using a labeled safety dataset. Second, using RL-as-inference strategy we derive an effective algorithm for optimizing a safe policy using the learned safety model. Finally, we devise a method to dynamically adapt the tradeoff coefficient between reward maximization and safety compliance. We rewrite the constrained optimization problem into its dual problem and derive a gradient-based method to dynamically adjust the tradeoff coefficient during training. Our empirical results demonstrate that this approach is highly scalable and able to satisfy sophisticated non-Markovian safety constraints.

Siow Meng Low, Akshat Kumar

In safe reinforcement learning (RL), auxiliary safety costs are used to align the agent to safe decision making. In practice, safety constraints, including cost functions and budgets, are unknown or hard to specify, as it requires anticipation of all possible unsafe behaviors. We therefore address a general setting where the true safety definition is unknown, and has to be learned from sparsely labeled data. Our key contributions are: first, we design a safety model that performs credit assignment to estimate each decision step's impact on the overall safety using a dataset of diverse trajectories and their corresponding binary safety labels (i.e., whether the corresponding trajectory is safe/unsafe). Second, we illustrate the architecture of our safety model to demonstrate its ability to learn a separate safety score for each timestep. Third, we reformulate the safe RL problem using the proposed safety model and derive an effective algorithm to optimize a safe yet rewarding policy. Finally, our empirical results corroborate our findings and show that this approach is effective in satisfying unknown safety definition, and scalable to various continuous control tasks.

Janaka Chathuranga Brahmanage, Jiajing Ling, Akshat Kumar

In many RL applications, ensuring an agent's actions adhere to constraints is crucial for safety. Most previous methods in Action-Constrained Reinforcement Learning (ACRL) employ a projection layer after the policy network to correct the action. However projection-based methods suffer from issues like the zero gradient problem and higher runtime due to the usage of optimization solvers. Recently methods were proposed to train generative models to learn a differentiable mapping between latent variables and feasible actions to address this issue. However, generative models require training using samples from the constrained action space, which itself is challenging. To address such limitations, first, we define a target distribution for feasible actions based on constraint violation signals, and train normalizing flows by minimizing the KL divergence between an approximated distribution over feasible actions and the target. This eliminates the need to generate feasible action samples, greatly simplifying the flow model learning. Second, we integrate the learned flow model with existing deep RL methods, which restrict it to exploring only the feasible action space. Third, we extend our approach beyond ACRL to handle state-wise constraints by learning the constraint violation signal from the environment. Empirically, our approach has significantly fewer constraint violations while achieving similar or better quality in several control tasks than previous best methods.

Mikhail Kazdagli, Mohit Tiwari, Akshat Kumar

Cloud computing services provide scalable and cost-effective solutions for data storage, processing, and collaboration. With their growing popularity, concerns about security vulnerabilities are increasing. To address this, first, we provide a formal model, called CloudLens, that expresses relations between different cloud objects such as users, datastores, security roles, representing access control policies in cloud systems. Second, as access control misconfigurations are often the primary driver for cloud attacks, we develop a planning model for detecting security vulnerabilities. Such vulnerabilities can lead to widespread attacks such as ransomware, sensitive data exfiltration among others. A planner generates attacks to identify such vulnerabilities in the cloud. Finally, we test our approach on 14 real Amazon AWS cloud configurations of different commercial organizations. Our system can identify a broad range of security vulnerabilities, which state-of-the-art industry tools cannot detect.

Mustafa Doga Dogan, Ahmad Taka, Michael Lu et al.

Existing approaches for embedding unobtrusive tags inside 3D objects require either complex fabrication or high-cost imaging equipment. We present InfraredTags, which are 2D markers and barcodes imperceptible to the naked eye that can be 3D printed as part of objects, and detected rapidly by low-cost near-infrared cameras. We achieve this by printing objects from an infrared-transmitting filament, which infrared cameras can see through, and by having air gaps inside for the tag's bits, which appear at a different intensity in the infrared image. We built a user interface that facilitates the integration of common tags (QR codes, ArUco markers) with the object geometry to make them 3D printable as InfraredTags. We also developed a low-cost infrared imaging module that augments existing mobile devices and decodes tags using our image processing pipeline. Our evaluation shows that the tags can be detected with little near-infrared illumination (0.2lux) and from distances as far as 250cm. We demonstrate how our method enables various applications, such as object tracking and embedding metadata for augmented reality and tangible interactions.

Akshat Kumar, Mohan Sarovar

We introduce an algorithm for computing geodesics on sampled manifolds that relies on simulation of quantum dynamics on a graph embedding of the sampled data. Our approach exploits classic results in semiclassical analysis and the quantum-classical correspondence, and forms a basis for techniques to learn the manifold from which a dataset is sampled, and subsequently for nonlinear dimensionality reduction of high-dimensional datasets. We illustrate the new algorithm with data sampled from model manifolds and also by a clustering demonstration based on COVID-19 mobility data. Finally, our method reveals interesting connections between the discretization provided by data sampling and quantization.

Jiajing Ling, Kushagra Chandak, Akshat Kumar

Solving multiagent problems can be an uphill task due to uncertainty in the environment, partial observability, and scalability of the problem at hand. Especially in an urban setting, there are more challenges since we also need to maintain safety for all users while minimizing congestion of the agents as well as their travel times. To this end, we tackle the problem of multiagent pathfinding under uncertainty and partial observability where the agents are tasked to move from their starting points to ending points while also satisfying some constraints, e.g., low congestion, and model it as a multiagent reinforcement learning problem. We compile the domain constraints using propositional logic and integrate them with the RL algorithms to enable fast simulation for RL.

Abhinav Bhatia, Pradeep Varakantham, Akshat Kumar

In urban environments, supply resources have to be constantly matched to the "right" locations (where customer demand is present) so as to improve quality of life. For instance, ambulances have to be matched to base stations regularly so as to reduce response time for emergency incidents in EMS (Emergency Management Systems); vehicles (cars, bikes, scooters etc.) have to be matched to docking stations so as to reduce lost demand in shared mobility systems. Such problem domains are challenging owing to the demand uncertainty, combinatorial action spaces (due to allocation) and constraints on allocation of resources (e.g., total resources, minimum and maximum number of resources at locations and regions). Existing systems typically employ myopic and greedy optimization approaches to optimize allocation of supply resources to locations. Such approaches typically are unable to handle surges or variances in demand patterns well. Recent research has demonstrated the ability of Deep RL methods in adapting well to highly uncertain environments. However, existing Deep RL methods are unable to handle combinatorial action spaces and constraints on allocation of resources. To that end, we have developed three approaches on top of the well known actor critic approach, DDPG (Deep Deterministic Policy Gradient) that are able to handle constraints on resource allocation. More importantly, we demonstrate that they are able to outperform leading approaches on simulators validated on semi-real and real data sets.

Duc Thien Nguyen, Akshat Kumar, Hoong Chuin Lau

Decentralized (PO)MDPs provide an expressive framework for sequential decision making in a multiagent system. Given their computational complexity, recent research has focused on tractable yet practical subclasses of Dec-POMDPs. We address such a subclass called CDEC-POMDP where the collective behavior of a population of agents affects the joint-reward and environment dynamics. Our main contribution is an actor-critic (AC) reinforcement learning method for optimizing CDEC-POMDP policies. Vanilla AC has slow convergence for larger problems. To address this, we show how a particular decomposition of the approximate action-value function over agents leads to effective updates, and also derive a new way to train the critic based on local reward signals. Comparisons on a synthetic benchmark and a real-world taxi fleet optimization problem show that our new AC approach provides better quality solutions than previous best approaches.

Xiaojian Wu, Akshat Kumar, Daniel Sheldon et al.

Stochastic network design is a general framework for optimizing network connectivity. It has several applications in computational sustainability including spatial conservation planning, pre-disaster network preparation, and river network optimization. A common assumption in previous work has been made that network parameters (e.g., probability of species colonization) are precisely known, which is unrealistic in real- world settings. We therefore address the robust river network design problem where the goal is to optimize river connectivity for fish movement by removing barriers. We assume that fish passability probabilities are known only imprecisely, but are within some interval bounds. We then develop a planning approach that computes the policies with either high robust ratio or low regret. Empirically, our approach scales well to large river networks. We also provide insights into the solutions generated by our robust approach, which has significantly higher robust ratio than the baseline solution with mean parameter estimates.

Akshat Kumar, Shlomo Zilberstein

Decentralized POMDPs provide an expressive framework for multi-agent sequential decision making. While fnite-horizon DECPOMDPs have enjoyed signifcant success, progress remains slow for the infnite-horizon case mainly due to the inherent complexity of optimizing stochastic controllers representing agent policies. We present a promising new class of algorithms for the infnite-horizon case, which recasts the optimization problem as inference in a mixture of DBNs. An attractive feature of this approach is the straightforward adoption of existing inference techniques in DBNs for solving DEC-POMDPs and supporting richer representations such as factored or continuous states and actions. We also derive the Expectation Maximization (EM) algorithm to optimize the joint policy represented as DBNs. Experiments on benchmark domains show that EM compares favorably against the state-of-the-art solvers.

Akshat Kumar, Shlomo Zilberstein

Computing maximum a posteriori (MAP) estimation in graphical models is an important inference problem with many applications. We present message-passing algorithms for quadratic programming (QP) formulations of MAP estimation for pairwise Markov random fields. In particular, we use the concave-convex procedure (CCCP) to obtain a locally optimal algorithm for the non-convex QP formulation. A similar technique is used to derive a globally convergent algorithm for the convex QP relaxation of MAP. We also show that a recently developed expectation-maximization (EM) algorithm for the QP formulation of MAP can be derived from the CCCP perspective. Experiments on synthetic and real-world problems confirm that our new approach is competitive with max-product and its variations. Compared with CPLEX, we achieve more than an order-of-magnitude speedup in solving optimally the convex QP relaxation.