Francesco Quinzan

Emmanouil Angelis, Francesco Quinzan, Ashkan Soleymani et al.

Learning the causes of time-series data is a fundamental task in many applications, spanning from finance to earth sciences or bio-medical applications. Common approaches for this task are based on vector auto-regression, and they do not take into account unknown confounding between potential causes. However, in settings with many potential causes and noisy data, these approaches may be substantially biased. Furthermore, potential causes may be correlated in practical applications or even contain cycles. To address these challenges, we propose a new double machine learning based method for structure identification from temporal data (DR-SIT). We provide theoretical guarantees, showing that our method asymptotically recovers the true underlying causal structure. Our analysis extends to cases where the potential causes have cycles, and they may even be confounded. We further perform extensive experiments to showcase the superior performance of our method. Code: https://github.com/sdi1100041/TMLR_submission_DR_SIT

Francesco Quinzan, Ashkan Soleymani, Patrick Jaillet et al.

Knowing the features of a complex system that are highly relevant to a particular target variable is of fundamental interest in many areas of science. Existing approaches are often limited to linear settings, sometimes lack guarantees, and in most cases, do not scale to the problem at hand, in particular to images. We propose DRCFS, a doubly robust feature selection method for identifying the causal features even in nonlinear and high dimensional settings. We provide theoretical guarantees, illustrate necessary conditions for our assumptions, and perform extensive experiments across a wide range of simulated and semi-synthetic datasets. DRCFS significantly outperforms existing state-of-the-art methods, selecting robust features even in challenging highly non-linear and high-dimensional problems.

Francesco Quinzan, Cecilia Casolo, Krikamol Muandet et al.

Notions of counterfactual invariance (CI) have proven essential for predictors that are fair, robust, and generalizable in the real world. We propose graphical criteria that yield a sufficient condition for a predictor to be counterfactually invariant in terms of a conditional independence in the observational distribution. In order to learn such predictors, we propose a model-agnostic framework, called Counterfactually Invariant Prediction (CIP), building on the Hilbert-Schmidt Conditional Independence Criterion (HSCIC), a kernel-based conditional dependence measure. Our experimental results demonstrate the effectiveness of CIP in enforcing counterfactual invariance across various simulated and real-world datasets including scalar and multi-variate settings.

Mary Chriselda Antony Oliver, Lan Jiang, Aaron Bundi Anampiu et al.

Adaptive orchestration of heterogeneous agents requires making sequential delegation decisions under uncertain and evolving agent behaviour, e.g., coordinating specialised AI models with varying reliability, cost, and response quality. While prior work on agent orchestration focuses on performance or cost, uncertainty in agent reliability and output distributions is typically not modelled explicitly at the orchestration level. In this work, we study the problem of adaptive orchestration of heterogeneous agents under uncertainty, where a meta-controller must decide when to delegate to an agent, accounting for reliability, cost, and uncertainty. We propose BOT-Orch, a lightweight framework that recasts orchestration as a bandit problem over agents, regularized by OT distances between agent output distributions and task-specific reference distributions. We show that the regularised orchestration enjoys $\mathcal{O}(\sqrt{T})$ regret under standard assumptions, and provably induces preference ordering among agents with identical mean rewards but differing distributional alignment. Empirically, we demonstrate that BOT-Orch outperforms standard bandit and heuristic baselines in synthetic but adversarial task allocation settings with heterogeneous, non-i.i.d. agent behaviour.

Shijin Gong, Erhan Xu, Kai Ye et al.

Reinforcement learning with verifiable rewards has become a standard recipe for improving the reasoning abilities of large language models. Existing algorithms face a tradeoff between computational efficiency and sample efficiency in value estimation and policy learning. We introduce BASIS, a critic-free post-training algorithm designed to address this tradeoff. At each online training step, BASIS samples only one rollout per prompt, but leverages rich information across prompts in the entire batch to improve value function estimation. Our experiments demonstrate that BASIS reduces MSE in value function estimation by 69% compared to REINFORCE++, a representative single-rollout baseline, and achieves lower MSE with one rollout than group mean estimators with 8 rollouts. This improvement in value estimation translates to better policy optimization: using substantially less training time, BASIS achieves performance close to multi-rollout GRPO-type baselines and often outperforms single-rollout REINFORCE-type baselines.

Rebecka Winqvist, Inês Lourenco, Francesco Quinzan et al.

The contribution of this paper is a generalized formulation of correctional learning using optimal transport, which is about how to optimally transport one mass distribution to another. Correctional learning is a framework developed to enhance the accuracy of parameter estimation processes by means of a teacher-student approach. In this framework, an expert agent, referred to as the teacher, modifies the data used by a learning agent, known as the student, to improve its estimation process. The objective of the teacher is to alter the data such that the student's estimation error is minimized, subject to a fixed intervention budget. Compared to existing formulations of correctional learning, our novel optimal transport approach provides several benefits. It allows for the estimation of more complex characteristics as well as the consideration of multiple intervention policies for the teacher. We evaluate our approach on two theoretical examples, and on a human-robot interaction application in which the teacher's role is to improve the robots performance in an inverse reinforcement learning setting.

Amir Mohammad Karimi Mamaghan, Andrea Dittadi, Stefan Bauer et al.

Causal reasoning can be considered a cornerstone of intelligent systems. Having access to an underlying causal graph comes with the promise of cause-effect estimation and the identification of efficient and safe interventions. However, learning causal representations remains a major challenge, due to the complexity of many real-world systems. Previous works on causal representation learning have mostly focused on Variational Auto-Encoders (VAE). These methods only provide representations from a point estimate, and they are unsuitable to handle high dimensions. To overcome these problems, we proposed a new Diffusion-based Causal Representation Learning (DCRL) algorithm. This algorithm uses diffusion-based representations for causal discovery. DCRL offers access to infinite dimensional latent codes, which encode different levels of information in the latent code. In a first proof of principle, we investigate the use of DCRL for causal representation learning. We further demonstrate experimentally that this approach performs comparably well in identifying the causal structure and causal variables.

Kai Ye, Hongyi Zhou, Jin Zhu et al.

Reinforcement learning from human feedback (RLHF) has emerged as a key technique for aligning the output of large language models (LLMs) with human preferences. To learn the reward function, most existing RLHF algorithms use the Bradley-Terry model, which relies on assumptions about human preferences that may not reflect the complexity and variability of real-world judgments. In this paper, we propose a robust algorithm to enhance the performance of existing approaches under such reward model misspecifications. Theoretically, our algorithm reduces the variance of reward and policy estimators, leading to improved regret bounds. Empirical evaluations on LLM benchmark datasets demonstrate that the proposed algorithm consistently outperforms existing methods, with 77-81% of responses being favored over baselines on the Anthropic Helpful and Harmless dataset. The code is available at https:// github.com/ VRPO/ VRPO.

Erhan Xu, Kai Ye, Hongyi Zhou et al.

This paper studies reinforcement learning from human feedback (RLHF) for aligning large language models with human preferences. While RLHF has demonstrated promising results, many algorithms are highly sensitive to misspecifications in the underlying preference model (e.g., the Bradley-Terry model), the reference policy, or the reward function, resulting in undesirable fine-tuning. To address model misspecification, we propose a doubly robust preference optimization algorithm that remains consistent when either the preference model or the reference policy is correctly specified (without requiring both). Our proposal demonstrates superior and more robust performance than state-of-the-art algorithms, both in theory and in practice. The code is available at https://github.com/DRPO4LLM/DRPO4LLM

Haroui Ma, Francesco Quinzan, Theresa Willem et al.

Machine learning (ML) systems for medical imaging have demonstrated remarkable diagnostic capabilities, but their susceptibility to biases poses significant risks, since biases may negatively impact generalization performance. In this paper, we introduce a novel statistical framework to evaluate the dependency of medical imaging ML models on sensitive attributes, such as demographics. Our method leverages the concept of counterfactual invariance, measuring the extent to which a model's predictions remain unchanged under hypothetical changes to sensitive attributes. We present a practical algorithm that combines conditional latent diffusion models with statistical hypothesis testing to identify and quantify such biases without requiring direct access to counterfactual data. Through experiments on synthetic datasets and large-scale real-world medical imaging datasets, including \textsc{cheXpert} and MIMIC-CXR, we demonstrate that our approach aligns closely with counterfactual fairness principles and outperforms standard baselines. This work provides a robust tool to ensure that ML diagnostic systems generalize well, e.g., across demographic groups, offering a critical step towards AI safety in healthcare. Code: https://github.com/Neferpitou3871/AI-Alignment-Medical-Imaging.

Anissa Alloula, Charles Jones, Zuzanna Wakefield-Skorniewska et al.

Unequal representation of demographic groups in training data poses challenges to model generalisation across populations. Standard practice assumes that balancing subgroup representation optimises performance. However, recent empirical results contradict this assumption: in some cases, imbalanced data distributions actually improve subgroup performance, while in others, subgroup performance remains unaffected by the absence of an entire subgroup during training. We conduct a systematic study of subgroup allocation across four vision and language models, varying training data composition to characterise the sensitivity of subgroup performance to data balance. We propose the latent separation hypothesis, which states that a partially fine-tuned model's dependence on subgroup representation is determined by the degree of separation between subgroups in the latent space of the pre-trained model. We formalise this hypothesis, provide theoretical analysis, and validate it empirically. Finally, we present a practical application to foundation model fine-tuning, demonstrating that quantitative analysis of latent subgroup separation can inform data collection and balancing decisions.

Umang Bhatt, Sanyam Kapoor, Mihir Upadhyay et al.

Strategies for orchestrating the interactions between multiple agents, both human and artificial, can wildly overestimate performance and underestimate the cost of orchestration. We design a framework to orchestrate agents under realistic conditions, such as inference costs or availability constraints. We show theoretically that orchestration is only effective if there are performance or cost differentials between agents. We then empirically demonstrate how orchestration between multiple agents can be helpful for selecting agents in a simulated environment, picking a learning strategy in the infamous Rogers' Paradox from social science, and outsourcing tasks to other agents during a question-answer task in a user study.

Daqian Shao, Ashkan Soleymani, Francesco Quinzan et al.

A common issue in learning decision-making policies in data-rich settings is spurious correlations in the offline dataset, which can be caused by hidden confounders. Instrumental variable (IV) regression, which utilises a key unconfounded variable known as the instrument, is a standard technique for learning causal relationships between confounded action, outcome, and context variables. Most recent IV regression algorithms use a two-stage approach, where a deep neural network (DNN) estimator learnt in the first stage is directly plugged into the second stage, in which another DNN is used to estimate the causal effect. Naively plugging the estimator can cause heavy bias in the second stage, especially when regularisation bias is present in the first stage estimator. We propose DML-IV, a non-linear IV regression method that reduces the bias in two-stage IV regressions and effectively learns high-performing policies. We derive a novel learning objective to reduce bias and design the DML-IV algorithm following the double/debiased machine learning (DML) framework. The learnt DML-IV estimator has strong convergence rate and $O(N^{-1/2})$ suboptimality guarantees that match those when the dataset is unconfounded. DML-IV outperforms state-of-the-art IV regression methods on IV regression benchmarks and learns high-performing policies in the presence of instruments.

James Pedley, Benjamin Etheridge, Stephen J. Roberts et al.

Reinforcement learning (RL) policies deployed in real-world environments must remain reliable under adversarial perturbations. At the same time, modern deep RL agents are heavily over-parameterized, raising costs and fragility concerns. While pruning has been shown to improve robustness in supervised learning, its role in adversarial RL remains poorly understood. We develop the first theoretical framework for certified robustness under pruning in state-adversarial Markov decision processes (SA-MDPs). For Gaussian and categorical policies with Lipschitz networks, we prove that element-wise pruning can only tighten certified robustness bounds; pruning never makes the policy less robust. Building on this, we derive a novel three-term regret decomposition that disentangles clean-task performance, pruning-induced performance loss, and robustness gains, exposing a fundamental performance--robustness frontier. Empirically, we evaluate magnitude and micro-pruning schedules on continuous-control benchmarks with strong policy-aware adversaries. Across tasks, pruning consistently uncovers reproducible ``sweet spots'' at moderate sparsity levels, where robustness improves substantially without harming - and sometimes even enhancing - clean performance. These results position pruning not merely as a compression tool but as a structural intervention for robust RL.

Daqian Shao, Ashkan Soleymani, Francesco Quinzan et al.

Solving conditional moment restrictions (CMRs) is a key problem considered in statistics, causal inference, and econometrics, where the aim is to solve for a function of interest that satisfies some conditional moment equalities. Specifically, many techniques for causal inference, such as instrumental variable (IV) regression and proximal causal learning (PCL), are CMR problems. Most CMR estimators use a two-stage approach, where the first-stage estimation is directly plugged into the second stage to estimate the function of interest. However, naively plugging in the first-stage estimator can cause heavy bias in the second stage. This is particularly the case for recently proposed CMR estimators that use deep neural network (DNN) estimators for both stages, where regularisation and overfitting bias is present. We propose DML-CMR, a two-stage CMR estimator that provides an unbiased estimate with fast convergence rate guarantees. We derive a novel learning objective to reduce bias and develop the DML-CMR algorithm following the double/debiased machine learning (DML) framework. We show that our DML-CMR estimator can achieve the minimax optimal convergence rate of $O(N^{-1/2})$ under parameterisation and mild regularity conditions, where $N$ is the sample size. We apply DML-CMR to a range of problems using DNN estimators, including IV regression and proximal causal learning on real-world datasets, demonstrating state-of-the-art performance against existing CMR estimators and algorithms tailored to those problems.

Francesco Quinzan, Rajiv Khanna, Moshik Hershcovitch et al.

We study the fundamental problem of selecting optimal features for model construction. This problem is computationally challenging on large datasets, even with the use of greedy algorithm variants. To address this challenge, we extend the adaptive query model, recently proposed for the greedy forward selection for submodular functions, to the faster paradigm of Orthogonal Matching Pursuit for non-submodular functions. The proposed algorithm achieves exponentially fast parallel run time in the adaptive query model, scaling much better than prior work. Furthermore, our extension allows the use of downward-closed constraints, which can be used to encode certain fairness criteria into the feature selection process. We prove strong approximation guarantees for the algorithm based on standard assumptions. These guarantees are applicable to many parametric models, including Generalized Linear Models. Finally, we demonstrate empirically that the proposed algorithm competes favorably with state-of-the-art techniques for feature selection, on real-world and synthetic datasets.

Francesco Quinzan, Vanja Doskoč, Andreas Göbel et al.

Several large-scale machine learning tasks, such as data summarization, can be approached by maximizing functions that satisfy submodularity. These optimization problems often involve complex side constraints, imposed by the underlying application. In this paper, we develop an algorithm with poly-logarithmic adaptivity for non-monotone submodular maximization under general side constraints. The adaptive complexity of a problem is the minimal number of sequential rounds required to achieve the objective. Our algorithm is suitable to maximize a non-monotone submodular function under a $p$-system side constraint, and it achieves a $(p + O(\sqrt{p}))$-approximation for this problem, after only poly-logarithmic adaptive rounds and polynomial queries to the valuation oracle function. Furthermore, our algorithm achieves a $(p + O(1))$-approximation when the given side constraint is a $p$-extendible system. This algorithm yields an exponential speed-up, with respect to the adaptivity, over any other known constant-factor approximation algorithm for this problem. It also competes with previous known results in terms of the query complexity. We perform various experiments on various real-world applications. We find that, in comparison with commonly used heuristics, our algorithm performs better on these instances.

Vanja Doskoč, Tobias Friedrich, Andreas Göbel et al.

We study the problem of maximizing a non-monotone submodular function under multiple knapsack constraints. We propose a simple discrete greedy algorithm to approach this problem, and prove that it yields strong approximation guarantees for functions with bounded curvature. In contrast to other heuristics, this requires no problem relaxation to continuous domains and it maintains a constant-factor approximation guarantee in the problem size. In the case of a single knapsack, our analysis suggests that the standard greedy can be used in non-monotone settings. Additionally, we study this problem in a dynamic setting, by which knapsacks change during the optimization process. We modify our greedy algorithm to avoid a complete restart at each constraint update. This modification retains the approximation guarantees of the static case. We evaluate our results experimentally on a video summarization and sensor placement task. We show that our proposed algorithm competes with the state-of-the-art in static settings. Furthermore, we show that in dynamic settings with tight computational time budget, our modified greedy yields significant improvements over starting the greedy from scratch, in terms of the solution quality achieved.

Ankit Chauhan, Tobias Friedrich, Francesco Quinzan

It has been observed that many complex real-world networks have certain properties, such as a high clustering coefficient, a low diameter, and a power-law degree distribution. A network with a power-law degree distribution is known as scale-free network. In order to study these networks, various random graph models have been proposed, e.g. Preferential Attachment, Chung-Lu, or Hyperbolic. We look at the interplay between the power-law degree distribution and the run time of optimization techniques for well known combinatorial problems. We observe that on scale-free networks, simple evolutionary algorithms (EAs) quickly reach a constant-factor approximation ratio on common covering problems We prove that the single-objective (1+1)EA reaches a constant-factor approximation ratio on the Minimum Dominating Set problem, the Minimum Vertex Cover problem, the Minimum Connected Dominating Set problem, and the Maximum Independent Set problem in expected polynomial number of calls to the fitness function. Furthermore, we prove that the multi-objective GSEMO algorithm reaches a better approximation ratio than the (1+1)EA on those problems, within polynomial fitness evaluations.