paper-with-me

Papers

Limitation of Characterizing Implicit Regularization by Data-independent Functions

2022-01-28 · Leyang Zhang, Zhi-Qin John Xu, Tao Luo, Yaoyu Zhang

In recent years, understanding the implicit regularization of neural networks (NNs) has become a central task in deep learning theory. However, implicit regularization is itself not completely defined and well understood. In this work, we attempt to mathematically define and study implicit regularization. Importantly, we explore the limitations of a common approach to characterizing implicit regularization using data-independent functions. We propose two dynamical mechanisms, i.e., Two-point and One-point Overlapping mechanisms, based on which we provide two recipes for producing classes of one-hidden-neuron NNs that provably cannot be fully characterized by a type of or all data-independent functions. Following the previous works, our results further emphasize the profound data dependency of implicit regularization in general, inspiring us to study in detail the data dependency of NN implicit regularization in the future.

📄 PDF Abstract BibTeX arXiv:2201.12198

Code (0)

등록된 구현이 없습니다.

Tasks

Learning Theory

Similar Papers 제목 키워드 기반

Implicit Regularization in Tensor Factorization

2021-02-19 · Noam Razin, Asaf Maman, Nadav Cohen

Recent efforts to unravel the mystery of implicit regularization in deep learning have led to a theoretical focus on matrix factorization -- matrix completion via linear neural network. As a step further towards practica…

Deep LearningMatrix Completion

Implicit Regularization in Deep Learning May Not Be Explainable by Norms

2020-05-13 · NeurIPS 2020 12 · Noam Razin, Nadav Cohen

Mathematically characterizing the implicit regularization induced by gradient-based optimization is a longstanding pursuit in the theory of deep learning. A widespread hope is that a characterization based on minimizatio…

Deep LearningMatrix CompletionOpen-Ended Question Answering

Estimating Implicit Regularization in Deep Learning

2026-05-06 · Joseph H. Rudoler, Kevin Tan, Giles Hooker, Konrad P. Kording arxiv

Deep learning systems are known to exhibit implicit regularization (alt. implicit bias), favoring simple solutions instead of merely minimizing the loss function. In some cases, we can analytically derive the implicit re…

A Unified Approach to Controlling Implicit Regularization via Mirror Descent

2023-06-24 · Haoyuan Sun, Khashayar Gatmiry, Kwangjun Ahn, Navid Azizan

Inspired by the remarkable success of large neural networks, there has been significant interest in understanding the generalization performance of over-parameterized models. Substantial efforts have been invested in cha…

Classificationregression

Optimal Rates of Convergence for Entropy Regularization in Discounted Markov Decision Processes

2024-06-06 · Johannes Müller, Semih Cayci

We study the error introduced by entropy regularization in infinite-horizon, discrete, discounted Markov decision processes. We show that this error decreases exponentially in the inverse regularization strength both in …

Policy Gradient Methods