Recent efforts at explaining the interplay of memorization and generaliz...
The transfer learning paradigm of model pre-training and subsequent
fine...
Deep neural networks may easily memorize noisy labels present in real-wo...
Recent works demonstrate that early layers in a neural network contain u...
In this paper we look into the conjecture of Entezari et al.(2021) which...
Large language models (LLMs) have shown increasing in-context learning
c...
This paper examines the impact of static sparsity on the robustness of a...
Real-world machine learning deployments are characterized by mismatches
...
In this paper, we conjecture that if the permutation invariance of neura...
Recent developments in large-scale machine learning suggest that by scal...
We focus on the problem of domain adaptation when the goal is shifting t...
We propose a new framework for reasoning about generalization in deep
le...
One desired capability for machines is the ability to transfer their
kno...
We study the phenomenon that some modules of deep neural networks (DNNs)...
We prove bounds on the generalization error of convolutional networks. T...
Machine learning (ML) techniques are enjoying rapidly increasing adoptio...
We analyze the joint probability distribution on the lengths of the vect...
We characterize the singular values of the linear transformation associa...
Given a knowledge base (KB) rich in facts about common nouns or generics...
We consider the problem of training input-output recurrent neural networ...
Training neural networks is a challenging non-convex optimization proble...
Community detection in graphs has been extensively studied both in theor...
Feature learning forms the cornerstone for tackling challenging learning...
We consider the problem of learning mixtures of generalized linear model...
Feature learning forms the cornerstone for tackling challenging learning...
We provide novel guaranteed approaches for training feedforward neural
n...
We propose an efficient ADMM method with guarantees for high-dimensional...