Publications

Preface
François Coste
Faissal Ouardi
Guillaume Rabusseau
2023-07-04
Proceedings of 16th edition of the International Conference on Grammatical Inference (published)
proceedings.mlr.press
proceedings.mlr.press
Generative Flow Networks: a Markov Chain Perspective
Tristan Deleu
Yoshua Bengio
2023-07-03
ArXiv (preprint)
doi.org
arxiv.org
Better Training of GFlowNets with Local Credit and Incomplete Trajectories
Ling Pan
Nikolay Malkin
Dinghuai Zhang
Yoshua Bengio
Generative Flow Networks or GFlowNets are related to Monte-Carlo Markov chain methods (as they sample from a distribution specified by an en… (see more)ergy function), reinforcement learning (as they learn a policy to sample composed objects through a sequence of steps), generative models (as they learn to represent and sample from a distribution) and amortized variational methods (as they can be used to learn to approximate and sample from an otherwise intractable posterior, given a prior and a likelihood). They are trained to generate an object
2023-07-02
Proceedings of the 40th International Conference on Machine Learning (published)
doi.org
proceedings.mlr.press
Bootstrapped Representations in Reinforcement Learning
Charline Le Lan
Stephen Tu
Mark Rowland
Anna Harutyunyan
Rishabh Agarwal
Bellemare Marc-Emmanuel
Will Dabney
In reinforcement learning (RL), state representations are key to dealing with large or continuous state spaces. While one of the promises of… (see more) deep learning algorithms is to automatically construct features well-tuned for the task they try to solve, such a representation might not emerge from end-to-end training of deep RL agents. To mitigate this issue, auxiliary objectives are often incorporated into the learning process and help shape the learnt state representation. Bootstrapping methods are today's method of choice to make these additional predictions. Yet, it is unclear which features these algorithms capture and how they relate to those from other auxiliary-task-based approaches. In this paper, we address this gap and provide a theoretical characterization of the state representation learnt by temporal difference learning (Sutton, 1988). Surprisingly, we find that this representation differs from the features learned by Monte Carlo and residual gradient algorithms for most transition structures of the environment in the policy evaluation setting. We describe the efficacy of these representations for policy evaluation, and use our theoretical analysis to design new auxiliary learning rules. We complement our theoretical results with an empirical comparison of these learning rules for different cumulant functions on classic domains such as the four-room domain (Sutton et al, 1999) and Mountain Car (Moore, 1990).
2023-07-02
Proceedings of the 40th International Conference on Machine Learning (published)
doi.org
proceedings.mlr.press
Convergence of Proximal Point and Extragradient-Based Methods Beyond Monotonicity: the Case of Negative Comonotonicity
Eduard Gorbunov
Adrien Taylor
Samuel Horváth
Gauthier Gidel
2023-07-02
Proceedings of the 40th International Conference on Machine Learning (published)
proceedings.mlr.press
proceedings.mlr.press
Graph Inductive Biases in Transformers without Message Passing
Liheng Ma
Chen Lin
Derek Lim
Adriana Romero
Puneet K. Dokania
Mark J. Coates
Philip Torr
Ser-Nam Lim
Transformers for graph data are increasingly widely studied and successful in numerous learning tasks. Graph inductive biases are crucial fo… (see more)r Graph Transformers, and previous works incorporate them using message-passing modules and/or positional encodings. However, Graph Transformers that use message-passing inherit known issues of message-passing, and differ significantly from Transformers used in other domains, thus making transfer of research advances more difficult. On the other hand, Graph Transformers without message-passing often perform poorly on smaller datasets, where inductive biases are more crucial. To bridge this gap, we propose the Graph Inductive bias Transformer (GRIT) — a new Graph Transformer that incorporates graph inductive biases without using message passing. GRIT is based on several architectural changes that are each theoretically and empirically justified, including: learned relative positional encodings initialized with random walk probabilities, a flexible attention mechanism that updates node and node-pair representations, and injection of degree information in each layer. We prove that GRIT is expressive — it can express shortest path distances and various graph propagation matrices. GRIT achieves state-of-the-art empirical performance across a variety of graph datasets, thus showing the power that Graph Transformers without message-passing can deliver.
2023-07-02
Proceedings of the 40th International Conference on Machine Learning (published)
doi.org
proceedings.mlr.press
Graphically Structured Diffusion Models
Christian Dietrich Weilbach
William Harvey
Frank N. Wood
2023-07-02
Proceedings of the 40th International Conference on Machine Learning (published)
doi.org
proceedings.mlr.press
Guided-topic modelling of single-cell transcriptomes enables sub-cell-type and disease-subtype deconvolution of bulk transcriptomes
Lakshmipuram Seshadri Swapna
Michael Huang
Yuemei Li
Cell-type composition is an important indicator of health. We present Guided Topic Model for deconvolution (GTM-decon) to automatically infe… (see more)r cell-type-specific gene topic distributions from single-cell RNA-seq data for deconvolving bulk transcriptomes. GTM-decon performs competitively on deconvolving simulated and real bulk data compared with the state-of-the-art methods. Moreover, as demonstrated in deconvolving disease transcriptomes, GTM-decon can infer multiple cell-type-specific gene topic distributions per cell type, which captures sub-cell-type variations. GTM-decon can also use phenotype labels from single-cell or bulk data as a guide to infer phenotype-specific gene distributions. In a nested-guided design, GTM-decon identified cell-type-specific differentially expressed genes from bulk breast cancer transcriptomes.
2023-07-02
bioRxiv (preprint)
doi.org
High-Probability Bounds for Stochastic Optimization and Variational Inequalities: the Case of Unbounded Variance
Abdurakhmon Sadiev
Marina Danilova
Eduard Gorbunov
Samuel Horváth
Gauthier Gidel
Pavel Dvurechensky
Alexander Gasnikov
Peter Richtárik
During the recent years the interest of optimization and machine learning communities in high-probability convergence of stochastic optimiza… (see more)tion methods has been growing. One of the main reasons for this is that high-probability complexity bounds are more accurate and less studied than in-expectation ones. However, SOTA high-probability non-asymptotic convergence results are derived under strong assumptions such as boundedness of the gradient noise variance or of the objective’s gradient itself. In this paper, we propose several algorithms with high-probability convergence results under less restrictive assumptions. In particular, we derive new high-probability convergence results under the assumption that the gradient/operator noise has bounded central
2023-07-02
Proceedings of the 40th International Conference on Machine Learning (published)
doi.org
proceedings.mlr.press
Hyena Hierarchy: Towards Larger Convolutional Language Models
Michael Poli
Stefano Massaroli
Eric Nguyen
Daniel Y Fu
Tri Dao
Stephen Baccus
Yoshua Bengio
Stefano Ermon
Christopher Re
2023-07-02
Proceedings of the 40th International Conference on Machine Learning (published)
doi.org
proceedings.mlr.press
Mechanistic Mode Connectivity
Ekdeep Singh Lubana
Eric J Bigelow
Robert P. Dick
David M. Krueger
Hidenori Tanaka
2023-07-02
Proceedings of the 40th International Conference on Machine Learning (published)
doi.org
proceedings.mlr.press
Nesterov Meets Optimism: Rate-Optimal Separable Minimax Optimization
Chris Junchi Li
Huizhuo Yuan
Angela Yuan
Gauthier Gidel
Quanquan Gu
Michael Jordan
We propose a new first-order optimization algorithm — AcceleratedGradient-OptimisticGradient (AG-OG) Descent Ascent—for separable convex… (see more)-concave minimax optimization. The main idea of our algorithm is to carefully leverage the structure of the minimax problem, performing Nesterov acceleration on the individual component and optimistic gradient on the coupling component. Equipped with proper restarting, we show that AG-OG achieves the optimal convergence rate (up to a constant) for a variety of settings, including bilinearly coupled strongly convex-strongly concave minimax optimization (bi-SC-SC), bilinearly coupled convex-strongly concave minimax optimization (bi-C-SC), and bilinear games. We also extend our algorithm to the stochastic setting and achieve the optimal convergence rate in both bi-SC-SC and bi-C-SC settings. AG-OG is the first single-call algorithm with optimal convergence rates in both deterministic and stochastic settings for bilinearly coupled minimax optimization problems.
2023-07-02
Proceedings of the 40th International Conference on Machine Learning (published)
proceedings.mlr.press
proceedings.mlr.press