research
∙
01/05/2023
Diagonalization Games
We study several variants of a combinatorial game which is based on Cant...
share
research
∙
10/04/2022
The Dynamics of Sharpness-Aware Minimization: Bouncing Across Ravines and Drifting Towards Wide Minima
We consider Sharpness-Aware Minimization (SAM), a gradient-based optimiz...
research
∙
09/29/2022
Compositional Semantic Parsing with Large Language Models
Humans can reason compositionally when presented with new tasks. Previou...
research
∙
08/31/2022
Fine-Grained Distribution-Dependent Learning Curves
Learning curves plot the expected error of a learning algorithm as a fun...
research
∙
05/21/2022
Least-to-Most Prompting Enables Complex Reasoning in Large Language Models
We propose a novel prompting strategy, least-to-most prompting, that ena...
research
∙
02/10/2022
Monotone Learning
The amount of training-data is one of the key factors which determines t...
research
∙
08/17/2021
Statistically Near-Optimal Hypothesis Selection
Hypothesis Selection is a fundamental distribution learning problem wher...
research
∙
11/09/2020
A Theory of Universal Learning
How quickly can a given class of concepts be learned from examples? It i...
research
∙
06/18/2020
What Do Neural Networks Learn When Trained With Random Labels?
We study deep neural networks (DNNs) trained on natural image data with ...
research
∙
05/24/2020
Proper Learning, Helly Number, and an Optimal SVM Bound
The classical PAC sample complexity bounds are stated for any Empirical ...
research
∙
02/26/2020
Predicting Neural Network Accuracy from Weights
We study the prediction of the accuracy of a neural network given only i...
research
∙
12/30/2019
Iterated Jackknives and Two-Sided Variance Inequalities
We consider the variance of a function of n independent random variables...
research
∙
12/20/2019
Measuring Compositional Generalization: A Comprehensive Method on Realistic Data
State-of-the-art machine learning methods exhibit limited compositional ...
research
∙
10/28/2019
Fast classification rates without standard margin assumptions
We consider the classical problem of learning rates for classes with fin...
research
∙
10/17/2019
Sharper bounds for uniformly stable algorithms
The generalization bounds for stable algorithms is a classical question ...
research
∙
07/25/2019
Google Research Football: A Novel Reinforcement Learning Environment
Recent progress in the field of reinforcement learning has been accelera...
research
∙
05/28/2019
When can unlabeled data improve the learning rate?
In semi-supervised classification, one is given access both to labeled a...
research
∙
05/27/2019
Practical and Consistent Estimation of f-Divergences
The estimation of an f-divergence between two probability distributions ...
research
∙
05/26/2019
Evaluating Generative Models Using Divergence Frontiers
Despite the tremendous progress in the estimation of generative models, ...
research
∙
02/10/2019
The Optimal Approximation Factor in Density Estimation
Consider the following problem: given two arbitrary densities q_1,q_2 an...
research
∙
02/09/2019
Passing Tests without Memorizing: Two Models for Fooling Discriminators
We introduce two mathematical frameworks for foolability in the context ...
research
∙
05/31/2018
Assessing Generative Models via Precision and Recall
Recent advances in generative modeling have led to an increased interest...
research
∙
03/22/2018
Gradient Descent Quantizes ReLU Network Features
Deep neural networks are often trained in the over-parametrized regime (...
research
∙
11/28/2017
Are GANs Created Equal? A Large-Scale Study
Generative adversarial networks (GAN) are a powerful subclass of generat...
research
∙
11/05/2017
Wasserstein Auto-Encoders
We propose the Wasserstein Auto-Encoder (WAE)---a new algorithm for buil...
research
∙
05/24/2017
Approximation and Convergence Properties of Generative Adversarial Learning
Generative adversarial networks (GAN) approximate a target data distribu...
research
∙
05/23/2017
Better Text Understanding Through Image-To-Text Transfer
Generic text embeddings are successfully used in a variety of tasks. How...
research
∙
05/22/2017
From optimal transport to generative modeling: the VEGAN cookbook
We study unsupervised generative modeling in terms of the optimal transp...
research
∙
01/09/2017