CORE MACHINE LEARNING

The SSL Interplay: Augmentations, Inductive Bias, and Generalization

June 26, 2023

Abstract

Self-supervised learning (SSL) has emerged as a powerful framework to learn representations from raw data without supervision. Yet in practice, engineers face issues such as instability in tuning optimizers and collapse of representations during training. Such challenges motivate the need for a theory to shed light on the complex interplay between the choice of data augmentation, network architecture, and training algorithm. We study such an interplay with a precise analysis of generalization performance on both pretraining and downstream tasks in a theory friendly setup, and highlight several insights for SSL practitioners that arise from our theory.

Download the Paper

AUTHORS

Written by

Vivien Cabannes

Bobak Kiani

Randall Balestriero

Yann LeCun

Alberto Bietti

Publisher

ICML

Research Topics

Core Machine Learning

Related Publications

July 08, 2024

THEORY

CORE MACHINE LEARNING

An Adaptive Stochastic Gradient Method with Non-negative Gauss-Newton Stepsizes

Antonio Orvieto, Lin Xiao

July 08, 2024

June 17, 2024

HUMAN & MACHINE INTELLIGENCE

COMPUTER VISION

D-Flow: Differentiating through Flows for Controlled Generation

Heli Ben-Hamu, Omri Puny, Itai Gat, Brian Karrer, Uriel Singer, Yaron Lipman

June 17, 2024

June 17, 2024

COMPUTER VISION

CORE MACHINE LEARNING

Bespoke Non-Stationary Solvers for Fast Sampling of Diffusion and Flow Models

Neta Shaul, Uriel Singer, Ricky Chen, Matt Le, Ali Thabet, Albert Pumarola, Yaron Lipman

June 17, 2024

June 14, 2024

CORE MACHINE LEARNING

Differentially Private Representation Learning via Image Captioning

Tom Sander, Yaodong Yu, Maziar Sanjabi, Alain Durmus, Yi Ma, Kamalika Chaudhuri, Chuan Guo

June 14, 2024

Help Us Pioneer The Future of AI

We share our open source frameworks, tools, libraries, and models for everything from research exploration to large-scale production deployment.