Guangwen Yang

Xin Wang, Wei Xue, Yilun Han et al.

Hybrid modeling combining data-driven techniques and numerical methods is an emerging and promising research direction for efficient climate simulation. However, previous works lack practical platforms, making developing hybrid modeling a challenging programming problem. Furthermore, the lack of standard data sets and evaluation metrics may hamper researchers from comprehensively comparing various algorithms under a uniform condition. To address these problems, we propose a framework called NeuroClim for hybrid modeling under the real-world scenario, a basic setting to simulate the real climate that we live in. NeuroClim consists of three parts: (1) Platform. We develop a user-friendly platform NeuroGCM for efficiently developing hybrid modeling in climate simulation. (2) Dataset. We provide an open-source dataset for data-driven methods in hybrid modeling. We investigate the characteristics of the data, i.e., heterogeneity and stiffness, which reveals the difficulty of regressing climate simulation data; (3) Metrics. We propose a methodology for quantitatively evaluating hybrid modeling, including the approximation ability of machine learning models and the stability during simulation. We believe that NeuroClim allows researchers to work without high level of climate-related expertise and focus only on machine learning algorithm design, which will accelerate hybrid modeling research in the AI-Climate intersection. The codes and data are released at https://github.com/x-w19/NeuroClim.

Yufan Jiang, Qiaozhi He, Xiaomin Zhuang et al. · tsinghua

Existing large language models have to run K times to generate a sequence of K tokens. In this paper, we present RecycleGPT, a generative language model with fast decoding speed by recycling pre-generated model states without running the whole model in multiple steps. Our approach relies on the observation that adjacent tokens in a sequence usually have strong correlations and the next token in a sequence can be reasonably guessed or inferred based on the preceding ones. Experiments and analysis demonstrate the effectiveness of our approach in lowering inference latency, achieving up to 1.4x speedup while preserving high performance.

Zheng Zhang, Yingsheng Ji, Jiachen Shen et al.

Risk assessment is a substantial problem for financial institutions that has been extensively studied both for its methodological richness and its various practical applications. With the expansion of inclusive finance, recent attentions are paid to micro and small-sized enterprises (MSEs). Compared with large companies, MSEs present a higher exposure rate to default owing to their insecure financial stability. Conventional efforts learn classifiers from historical data with elaborate feature engineering. However, the main obstacle for MSEs involves severe deficiency in credit-related information, which may degrade the performance of prediction. Besides, financial activities have diverse explicit and implicit relations, which have not been fully exploited for risk judgement in commercial banks. In particular, the observations on real data show that various relationships between company users have additional power in financial risk analysis. In this paper, we consider a graph of banking data, and propose a novel HIDAM model for the purpose. Specifically, we attempt to incorporate heterogeneous information network with rich attributes on multi-typed nodes and links for modeling the scenario of business banking service. To enhance feature representation of MSEs, we extract interactive information through meta-paths and fully exploit path information. Furthermore, we devise a hierarchical attention mechanism respectively to learn the importance of contents inside each meta-path and the importance of different metapahs. Experimental results verify that HIDAM outperforms state-of-the-art competitors on real-world banking data.

Haoyu Ma, Yushu Chen, Wenlai Zhao et al. · tsinghua

Time series foundation models have demonstrated strong performance in zero-shot learning, making them well-suited for predicting rapidly evolving patterns in real-world applications where relevant training data are scarce. However, most of these models rely on the Transformer architecture, which incurs quadratic complexity as input length increases. To address this, we introduce TSMamba, a linear-complexity foundation model for time series forecasting built on the Mamba architecture. The model captures temporal dependencies through both forward and backward Mamba encoders, achieving high prediction accuracy. To reduce reliance on large datasets and lower training costs, TSMamba employs a two-stage transfer learning process that leverages pretrained Mamba LLMs, allowing effective time series modeling with a moderate training set. In the first stage, the forward and backward backbones are optimized via patch-wise autoregressive prediction; in the second stage, the model trains a prediction head and refines other components for long-term forecasting. While the backbone assumes channel independence to manage varying channel numbers across datasets, a channel-wise compressed attention module is introduced to capture cross-channel dependencies during fine-tuning on specific multivariate datasets. Experiments show that TSMamba's zero-shot performance is comparable to state-of-the-art time series foundation models, despite using significantly less training data. It also achieves competitive or superior full-shot performance compared to task-specific prediction models. The code will be made publicly available.

Yushu Chen, Shengzhuo Liu, Jinzhe Yang et al.

In order to enhance the performance of Transformer models for long-term multivariate forecasting while minimizing computational demands, this paper introduces the Joint Time-Frequency Domain Transformer (JTFT). JTFT combines time and frequency domain representations to make predictions. The frequency domain representation efficiently extracts multi-scale dependencies while maintaining sparsity by utilizing a small number of learnable frequencies. Simultaneously, the time domain (TD) representation is derived from a fixed number of the most recent data points, strengthening the modeling of local relationships and mitigating the effects of non-stationarity. Importantly, the length of the representation remains independent of the input sequence length, enabling JTFT to achieve linear computational complexity. Furthermore, a low-rank attention layer is proposed to efficiently capture cross-dimensional dependencies, thus preventing performance degradation resulting from the entanglement of temporal and channel-wise modeling. Experimental results on six real-world datasets demonstrate that JTFT outperforms state-of-the-art baselines in predictive performance.

Zichuan Lin, Garrett Thomas, Guangwen Yang et al.

Meta-reinforcement learning (meta-RL) aims to learn from multiple training tasks the ability to adapt efficiently to unseen test tasks. Despite the success, existing meta-RL algorithms are known to be sensitive to the task distribution shift. When the test task distribution is different from the training task distribution, the performance may degrade significantly. To address this issue, this paper proposes Model-based Adversarial Meta-Reinforcement Learning (AdMRL), where we aim to minimize the worst-case sub-optimality gap -- the difference between the optimal return and the return that the algorithm achieves after adaptation -- across all tasks in a family of tasks, with a model-based approach. We propose a minimax objective and optimize it by alternating between learning the dynamics model on a fixed task and finding the adversarial task for the current model -- the task for which the policy induced by the model is maximally suboptimal. Assuming the family of tasks is parameterized, we derive a formula for the gradient of the suboptimality with respect to the task parameters via the implicit function theorem, and show how the gradient estimator can be efficiently implemented by the conjugate gradient method and a novel use of the REINFORCE estimator. We evaluate our approach on several continuous control benchmarks and demonstrate its efficacy in the worst-case performance over all tasks, the generalization power to out-of-distribution tasks, and in training and test time sample efficiency, over existing state-of-the-art meta-RL algorithms.

Zichuan Lin, Li Zhao, Derek Yang et al.

Many reinforcement learning (RL) tasks have specific properties that can be leveraged to modify existing RL algorithms to adapt to those tasks and further improve performance, and a general class of such properties is the multiple reward channel. In those environments the full reward can be decomposed into sub-rewards obtained from different channels. Existing work on reward decomposition either requires prior knowledge of the environment to decompose the full reward, or decomposes reward without prior knowledge but with degraded performance. In this paper, we propose Distributional Reward Decomposition for Reinforcement Learning (DRDRL), a novel reward decomposition algorithm which captures the multiple reward channel structure under distributional setting. Empirically, our method captures the multi-channel structure and discovers meaningful reward decomposition, without any requirements on prior knowledge. Consequently, our agent achieves better performance than existing methods on environments with multiple reward channels.

Yushu Chen, Hao Jing, Wenlai Zhao et al.

We present the remote stochastic gradient (RSG) method, which computes the gradients at configurable remote observation points, in order to improve the convergence rate and suppress gradient noise at the same time for different curvatures. RSG is further combined with adaptive methods to construct ARSG for acceleration. The method is efficient in computation and memory, and is straightforward to implement. We analyze the convergence properties by modeling the training process as a dynamic system, which provides a guideline to select the configurable observation factor without grid search. ARSG yields $O(1/\sqrt{T})$ convergence rate in non-convex settings, that can be further improved to $O(\log(T)/T)$ in strongly convex settings. Numerical experiments demonstrate that ARSG achieves both faster convergence and better generalization, compared with popular adaptive methods, such as ADAM, NADAM, AMSGRAD, and RANGER for the tested problems. In particular, for training ResNet-50 on ImageNet, ARSG outperforms ADAM in convergence speed and meanwhile it surpasses SGD in generalization.

Mingzhen Li, Changxi Liu, Jianjin Liao et al.

The flourish of deep learning frameworks and hardware platforms has been demanding an efficient compiler that can shield the diversity in both software and hardware in order to provide application portability. Among the existing deep learning compilers, TVM is well known for its efficiency in code generation and optimization across diverse hardware devices. In the meanwhile, the Sunway many-core processor renders itself as a competitive candidate for its attractive computational power in both scientific computing and deep learning workloads. This paper combines the trends in these two directions. Specifically, we propose swTVM that extends the original TVM to support ahead-of-time compilation for architecture requiring cross-compilation such as Sunway. In addition, we leverage the architecture features during the compilation such as core group for massive parallelism, DMA for high bandwidth memory transfer and local device memory for data locality, in order to generate efficient codes for deep learning workloads on Sunway. The experiment results show that the codes generated by swTVM achieves 1.79x on average compared to the state-of-the-art deep learning framework on Sunway, across six representative benchmarks. This work is the first attempt from the compiler perspective to bridge the gap of deep learning and Sunway processor particularly with productivity and efficiency in mind. We believe this work will encourage more people to embrace the power of deep learning and Sunway many-core processor.

Benjamin Doerr, Weijie Zheng

We conduct a first fundamental analysis of the working principles of binary differential evolution (BDE), an optimization heuristic for binary decision variables that was derived by Gong and Tuson (2007) from the very successful classic differential evolution (DE) for continuous optimization. We show that unlike most other optimization paradigms, it is stable in the sense that neutral bit values are sampled with probability close to $1/2$ for a long time. This is generally a desirable property, however, it makes it harder to find the optima for decision variables with small influence on the objective function. This can result in an optimization time exponential in the dimension when optimizing simple symmetric functions like OneMax. On the positive side, BDE quickly detects and optimizes the most important decision variables. For example, dominant bits converge to the optimal value in time logarithmic in the population size. This enables BDE to optimize the most important bits very fast. Overall, our results indicate that BDE is an interesting optimization paradigm having characteristics significantly different from classic evolutionary algorithms or estimation-of-distribution algorithms (EDAs). On the technical side, we observe that the strong stochastic dependencies in the random experiment describing a run of BDE prevent us from proving all desired results with the mathematical rigor that was successfully used in the analysis of other evolutionary algorithms. Inspired by mean-field approaches in statistical physics we propose a more independent variant of BDE, show experimentally its similarity to BDE, and prove some statements rigorously only for the independent variant. Such a semi-rigorous approach might be interesting for other problems in evolutionary computation where purely mathematical methods failed so far.

Zichuan Lin, Tianqi Zhao, Guangwen Yang et al.

Reinforcement learning (RL) algorithms have made huge progress in recent years by leveraging the power of deep neural networks (DNN). Despite the success, deep RL algorithms are known to be sample inefficient, often requiring many rounds of interaction with the environments to obtain satisfactory performance. Recently, episodic memory based RL has attracted attention due to its ability to latch on good actions quickly. In this paper, we present a simple yet effective biologically inspired RL algorithm called Episodic Memory Deep Q-Networks (EMDQN), which leverages episodic memory to supervise an agent during training. Experiments show that our proposed method can lead to better sample efficiency and is more likely to find good policies. It only requires 1/5 of the interactions of DQN to achieve many state-of-the-art performances on Atari games, significantly outperforming regular DQN and other episodic memory based RL algorithms.