paper-with-me

홈 › Papers

On Generalization Bounds for Neural Networks with Low Rank Layers

2024-11-20 · Andrea Pinto, Akshay Rangamani, Tomaso Poggio

While previous optimization results have suggested that deep neural networks tend to favour low-rank weight matrices, the implications of this inductive bias on generalization bounds remain underexplored. In this paper, we apply Maurer's chain rule for Gaussian complexity to analyze how low-rank layers in deep networks can prevent the accumulation of rank and dimensionality factors that typically multiply across layers. This approach yields generalization bounds for rank and spectral norm constrained networks. We compare our results to prior generalization bounds for deep networks, highlighting how deep networks with low-rank layers can achieve better generalization than those with full-rank layers. Additionally, we discuss how this framework provides new perspectives on the generalization capabilities of deep networks exhibiting neural collapse.

📄 PDF Abstract BibTeX arXiv:2411.13733

Code (0)

등록된 구현이 없습니다.

Tasks

Generalization BoundsInductive Bias

Similar Papers 제목 키워드 기반

Transformed Low-Rank Parameterization Can Help Robust Generalization for Tensor Neural Networks

2023-03-01 · NeurIPS 2023 11 · Andong Wang, Chao Li, Mingyuan Bai, Zhong Jin 외

Achieving efficient and robust multi-channel data learning is a challenging task in data science. By exploiting low-rankness in the transformed domain, i.e., transformed low-rankness, tensor Singular Value Decomposition …

Generalization Bounds

Koopman-based generalization bound: New aspect for full-rank weights

2023-02-12 · Yuka Hashimoto, Sho Sonoda, Isao Ishikawa, Atsushi Nitanda 외

We propose a new bound for generalization of neural networks using Koopman operators. Whereas most of existing works focus on low-rank weight matrices, we focus on full-rank weight matrices. Our bound is tighter than exi…

Generalization error bounds for learning to rank: Does the length of document lists matter?

2016-03-06 · Ambuj Tewari, Sougata Chaudhuri

We consider the generalization ability of algorithms for learning to rank at a query level, a problem also called subset ranking. Existing generalization error bounds necessarily degrade as the size of the document list …

Learning-To-Rank

Two-Layer Generalization Analysis for Ranking Using Rademacher Average

2010-12-01 · NeurIPS 2010 12 · Wei Chen, Tie-Yan Liu, Zhi-Ming Ma

This paper is concerned with the generalization analysis on learning to rank for information retrieval (IR). In IR, data are hierarchically organized, i.e., consisting of queries and documents per query. Previous general…

Generalization BoundsInformation RetrievalLearning-To-RankRetrieval+1

Depth-Bounds for Neural Networks via the Braid Arrangement

2025-02-13 · Moritz Grillo, Christoph Hertrich, Georg Loho

We contribute towards resolving the open question of how many hidden layers are required in ReLU networks for exactly representing all continuous and piecewise linear functions on $\mathbb{R}^d$. While the question has b…