NLP in the era of generative AI, cognitive sciences, and societal transformation
Join us at Mila in October for a three-day workshop to explore the transformative potential of language technologies and their implications for society.
This program is designed to provide decision-makers, policymakers and professional working in policy with a foundational understanding of AI technology.
We use cookies to analyze the browsing and usage of our website and to personalize your experience. You can disable these technologies at any time, but this may limit certain functionalities of the site. Read our Privacy Policy for more information.
Setting cookies
You can enable and disable the types of cookies you wish to accept. However certain choices you make could affect the services offered on our sites (e.g. suggestions, personalised ads, etc.).
Essential cookies
These cookies are necessary for the operation of the site and cannot be deactivated. (Still active)
Analytics cookies
Do you accept the use of cookies to measure the audience of our sites?
Multimedia Player
Do you accept the use of cookies to display and allow you to watch the video content hosted by our partners (YouTube, etc.)?
Publications
Multi-Environment Pretraining Enables Transfer to Action Limited Datasets
Using massive datasets to train large-scale models has emerged as a dominant approach for broad generalization in natural language an… (see more)d vision applications. In reinforcement learning, however, a key challenge is that available data of sequential decision making is often not annotated with actions - for example, videos of game-play are much more available than sequences of frames paired with the logged game controls. We propose to circumvent this challenge by combining large but sparsely-annotated datasets from a \emph{target} environment of interest with fully-annotated datasets from various other \emph{source} environments. Our method, Action Limited PreTraining (ALPT), leverages the generalization capabilities of inverse dynamics modelling (IDM) to label missing action data in the target environment. We show that utilizing even one additional environment dataset of labelled data during IDM pretraining gives rise to substantial improvements in generating action labels for unannotated sequences. We evaluate our method on benchmark game-playing environments and show that we can significantly improve game performance and generalization capability compared to other approaches, even when using annotated datasets equivalent to only 12 minutes of gameplay.
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.
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.
. Neural activity tends to reside on manifolds whose dimension is much lower than the dimension of the whole neural state space. Experiments… (see more) using brain-computer interfaces with microelectrode arrays implanted in the motor cortex of nonhuman primates tested the hypothesis that external perturbations should produce different adaptation strategies depending on how “aligned” the perturbation is with respect to a pre-existing intrinsic manifold. On the one hand, perturbations within the manifold (WM) evoked fast reassociations of existing patterns for rapid adaptation. On the other hand, perturbations outside the manifold (OM) triggered the slow emergence of new neural patterns underlying a much slower—and, without adequate training protocols, inconsistent or virtually impossible—adaptation. This suggests that the time scale and the overall difficulty of the brain to adapt depend fundamentally on the structure of neural activity. Here, we used a simplified static Gaussian model to show that gradient-descent learning could explain the differences between adaptation to WM and OM perturbations. For small learning rates, we found that the adaptation speeds were different but the model eventually adapted to both perturbations. Moreover, sufficiently large learning rates could entirely prohibit adaptation to OM perturbations while preserving adaptation to WM perturbations, in agreement with experiments. Adopting an incremental training protocol, as has been done in experiments, permitted a swift recovery of a full adaptation in the cases where OM perturbations were previously impossible to relearn. Finally, we also found that gradient descent was compatible with the reassociation mechanism on short adaptation time scales. Since gradient descent has many biologically plausible variants, our findings thus establish gradient-based learning as a plausible mechanism for adaptation under network-level constraints, with a central role for the learning rate.
. Neural activity tends to reside on manifolds whose dimension is much lower than the dimension of the whole neural state space. Experiments… (see more) using brain-computer interfaces with microelectrode arrays implanted in the motor cortex of nonhuman primates tested the hypothesis that external perturbations should produce different adaptation strategies depending on how “aligned” the perturbation is with respect to a pre-existing intrinsic manifold. On the one hand, perturbations within the manifold (WM) evoked fast reassociations of existing patterns for rapid adaptation. On the other hand, perturbations outside the manifold (OM) triggered the slow emergence of new neural patterns underlying a much slower—and, without adequate training protocols, inconsistent or virtually impossible—adaptation. This suggests that the time scale and the overall difficulty of the brain to adapt depend fundamentally on the structure of neural activity. Here, we used a simplified static Gaussian model to show that gradient-descent learning could explain the differences between adaptation to WM and OM perturbations. For small learning rates, we found that the adaptation speeds were different but the model eventually adapted to both perturbations. Moreover, sufficiently large learning rates could entirely prohibit adaptation to OM perturbations while preserving adaptation to WM perturbations, in agreement with experiments. Adopting an incremental training protocol, as has been done in experiments, permitted a swift recovery of a full adaptation in the cases where OM perturbations were previously impossible to relearn. Finally, we also found that gradient descent was compatible with the reassociation mechanism on short adaptation time scales. Since gradient descent has many biologically plausible variants, our findings thus establish gradient-based learning as a plausible mechanism for adaptation under network-level constraints, with a central role for the learning rate.
(1) N (x; θ) = Ll+1 ○ σl ○Ll ○ σl−1 ○ . . . ○ σ1 ○L1. The symbol Lk denotes the k’s affine operator of the form Lk(x) = … (see more)Akx + bk, while σk denotes a nonlinear function called an activation function. The activation functions are chosen by the user. The matrices Ak and shift vectors (or bias vectors) bk are encoded into the argument θ: θ = {Ak, bk} l+1 k=1. The term training neural network means finding {Ak, bk} l+1 k=1 such that N (x; θ) satisfies certain conditions. These conditions are described by the loss function chosen by the user. For example, one might want the neural network to assume certain values fj at certain points xj , j = 1, . . . ,N . These points x are called the training data. In this case, a common choice of the loss function is the least squares error:
Opinion summarization research has primar-001 ily focused on generating summaries reflect-002 ing important opinions from customer reviews 0… (see more)03 without paying much attention to the writing 004 style. In this paper, we propose the stylized 005 opinion summarization task, which aims to 006 generate a summary of customer reviews in 007 the desired (e.g., professional) writing style. 008 To tackle the difficulty in collecting customer 009 and professional review pairs, we develop a 010 non-parallel training framework, Noisy Pair-011 ing and Partial Supervision ( NAPA ), which 012 trains a stylized opinion summarization sys-013 tem from non-parallel customer and profes-014 sional review sets. We create a benchmark P RO - 015 S UM by collecting customer and professional 016 reviews from Yelp and Michelin. Experimental 017 results on P RO S UM and FewSum demonstrate 018 that our non-parallel training framework con-019 sistently improves both automatic and human 020 evaluations, successfully building a stylized 021 opinion summarization model that can gener-022 ate professionally-written summaries from cus-023 tomer reviews. 024
Sharpness-aware minimization (SAM) was proposed to reduce sharpness of minima and has been shown to enhance generalization performance in va… (see more)rious settings. In this work we show that perturbing only the affine normalization parameters (typically comprising 0.1% of the total parameters) in the adversarial step of SAM can outperform perturbing all of the parameters.This finding generalizes to different SAM variants and both ResNet (Batch Normalization) and Vision Transformer (Layer Normalization) architectures. We consider alternative sparse perturbation approaches and find that these do not achieve similar performance enhancement at such extreme sparsity levels, showing that this behaviour is unique to the normalization layers. Although our findings reaffirm the effectiveness of SAM in improving generalization performance, they cast doubt on whether this is solely caused by reduced sharpness.