Publications

Publication

July 18, 2021

CORE MACHINE LEARNING

Marginalized Stochastic Natural Gradients for Black-Box Variational Inference

Black-box variational inference algorithms use stochastic sampling to analyze diverse statistical models, like those expressed in probabilistic programming languages …

Geng Ji, Debora Sujono, Erik B. Sudderth

July 18, 2021

Publication

July 18, 2021

COMPUTER VISION

Multi-Task Reinforcement Learning with Context-based Representations

The benefit of multi-task learning over single-task learning relies on the ability to use relations across tasks to improve performance on any single task …

Shagun Sodhani, Amy Zhang, Joelle Pineau

July 18, 2021

Publication

July 18, 2021

CORE MACHINE LEARNING

Align, then memorise: the dynamics of learning with feedback alignment

Direct Feedback Alignment (DFA) is emerging as an efficient and biologically plausible alternative to backpropagation for training deep neural networks. …

Maria Refinetti, Stephane d’Ascoli, Ruben Ohana, Sebastian Goldt

July 18, 2021

Publication

July 18, 2021

CORE MACHINE LEARNING

ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases

Convolutional architectures have proven extremely successful for vision tasks. Their hard inductive biases enable sample-efficient learning …

Stephane d’Ascoli, Hugo Touvron, Matthew L. Leavitt, Ari S. Morcos, Giulio Biroli, Levent Sagun

July 18, 2021

Publication

July 18, 2021

CORE MACHINE LEARNING

CombOptNet: Fit the Right NP-Hard Problem by Learning Integer Programming Constraints

Bridging logical and algorithmic reasoning with modern machine learning techniques is a fundamental challenge with potentially transformative impact …

Anselm Paulus, Michal Rolínek, Vít Musil, Brandon Amos, Georg Martius

July 18, 2021

Publication

July 18, 2021

COMPUTER VISION

AlphaNet: Improved Training of Supernets with Alpha-Divergence

Weight-sharing neural architecture search (NAS) is an effective technique for automating efficient neural architecture design. …

Dilin Wang, Chengyue Gong, Meng Li, Qiang Liu, Vikas Chandra

July 18, 2021

Publication

July 18, 2021

GRAPHICS

COMPUTER VISION

Improving Lossless Compression Rates via Monte Carlo Bits-Back Coding

Latent variable models have been successfully applied in lossless compression with the bits-back coding algorithm …

Yangjun Ruan, Karen Ullrich, Daniel Severo, James Townsend, Ashish Khisti, Arnaud Doucet, Alireza Makhzani, Chris J. Maddison

July 18, 2021

Publication

July 18, 2021

COMPUTER VISION

Barlow Twins: Self-Supervised Learning via Redundancy Reduction

Self-supervised learning (SSL) is rapidly closing the gap with supervised methods on large computer vision benchmarks …

Jure Zbontar, Li Jing, Ishan Misra Yann LeCun, Stephane Deny ´ 1

July 18, 2021

Publication

July 18, 2021

CORE MACHINE LEARNING

THEORY

Near-Optimal Confidence Sequences for Bounded Random Variables

Many inference problems, such as sequential decision problems like A/B testing, adaptive sampling schemes like bandit selection …

Arun Kumar Kuchibhotla, Qinqing Zheng

July 18, 2021

Publication

July 18, 2021

CORE MACHINE LEARNING

Riemannian Convex Potential Maps

Modeling distributions on Riemannian manifolds is a crucial component in understanding non-Euclidean data that arises …

Samuel Cohen, Brandon Amos, Yaron Lipman

July 18, 2021

Publication

July 17, 2021

COMPUTER VISION

Prioritized Level Replay

Environments with procedurally generated content serve as important benchmarks for testing systematic generalization in deep reinforcement learning …

Minqi Jiang, Edward Grefenstette, Tim Rocktaschel

July 17, 2021

Publication

July 17, 2021

CORE MACHINE LEARNING

Recovering AES Keys with a Deep Cold Boot Attack

Cold boot attacks inspect the corrupted random access memory soon after the power has been shut down …

Itamar Zimerman, Eliya Nachmani, Lior Wolf

July 17, 2021

Frameworks & Tools

Recent Publications

Fundamental & Applied

Recent Projects

People Profiles

AI Residency Program

Tools

Tools Frameworks & Tools

Research

Research Research Areas Notable Papers Recent Publications Fundamental & Applied Recent Projects

Blog

People

People People Profiles

Join Us

Join Us Jobs AI Residency Program RAISE Program

Facebook © 2021