paper-with-me

Papers

For self-supervised learning, Rationality implies generalization, provably

2020-10-16 · ICLR 2021 1 · Yamini Bansal, Gal Kaplun, Boaz Barak

We prove a new upper bound on the generalization gap of classifiers that are obtained by first using self-supervision to learn a representation $r$ of the training data, and then fitting a simple (e.g., linear) classifier $g$ to the labels. Specifically, we show that (under the assumptions described below) the generalization gap of such classifiers tends to zero if $\mathsf{C}(g) \ll n$, where $\mathsf{C}(g)$ is an appropriately-defined measure of the simple classifier $g$'s complexity, and $n$ is the number of training samples. We stress that our bound is independent of the complexity of the representation $r$. We do not make any structural or conditional-independence assumptions on the representation-learning task, which can use the same training dataset that is later used for classification. Rather, we assume that the training procedure satisfies certain natural noise-robustness (adding small amount of label noise causes small degradation in performance) and rationality (getting the wrong label is not better than getting no label at all) conditions that widely hold across many standard architectures. We show that our bound is non-vacuous for many popular representation-learning based classifiers on CIFAR-10 and ImageNet, including SimCLR, AMDIM and MoCo.

📄 PDF Abstract BibTeX arXiv:2010.08508

Code (2)

ICLR2021-rep-gen/Rationality-Generalization 공식 구현 pytorch
https://gitlab.com/harvard-machine-learning/rationality-generalization 공식 구현 pytorch

Tasks

Representation LearningSelf-Supervised Learning

Methods 이 논문이 사용한 방법론

1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Average Pooling 설명 없음
Residual Connection 설명 없음
Residual Block Residual Blocks are skip-connection blocks that learn residual functions with reference to the layer inputs, instead of learning unreferenced functions. They were introduced…
Bottleneck Residual Block A Bottleneck Residual Block is a variant of the residual block that utilises 1x1 convolutions to create a bottleneck. The…
Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Kaiming Initialization 설명 없음

Similar Papers 제목 키워드 기반

Strategically Robust Multi-Agent Reinforcement Learning with Linear Function Approximation

2026-03-10 · Jake Gonzales, Max Horwitz, Eric Mazumdar, Lillian J. Ratliff arxiv

Provably efficient and robust equilibrium computation in general-sum Markov games remains a core challenge in multi-agent reinforcement learning. Nash equilibrium is computationally intractable in general and brittle due…

Multi-agent Reinforcement Learning

Robustness Implies Generalization via Data-Dependent Generalization Bounds

2022-06-27 · Kenji Kawaguchi, Zhun Deng, Kyle Luh, Jiaoyang Huang

This paper proves that robustness implies generalization via data-dependent generalization bounds. As a result, robustness and generalization are shown to be connected closely in a data-dependent manner. Our bounds impro…

Generalization Bounds

Object Placement for Anything

2025-04-16 · Bingjie Gao, Bo Zhang, Li Niu

Object placement aims to determine the appropriate placement (\emph{e.g.}, location and size) of a foreground object when placing it on the background image. Most previous works are limited by small-scale labeled dataset…

Object

Sharpness Minimization Algorithms Do Not Only Minimize Sharpness To Achieve Better Generalization

2023-07-20 · NeurIPS 2023 11

Despite extensive studies, the underlying reason as to why overparameterized neural networks can generalize remains elusive. Existing theory shows that common stochastic optimizers prefer flatter minimizers of the traini…

In-Token Rationality Optimization: Towards Accurate and Concise LLM Reasoning via Self-Feedback

2025-11-13 · Mingye Zhu, Yi Liu, Zheren Fu, Quan Wang 외 arxiv

Training Large Language Models (LLMs) for chain-of-thought reasoning presents a significant challenge: supervised fine-tuning on a single "golden" rationale hurts generalization as it penalizes equally valid alternatives…

Reinforcement Learning