paper-with-me

Papers

Efficiently testing local optimality and escaping saddles for ReLU networks

2018-09-28 · ICLR 2019 5 · Chulhee Yun, Suvrit Sra, Ali Jadbabaie

We provide a theoretical algorithm for checking local optimality and escaping saddles at nondifferentiable points of empirical risks of two-layer ReLU networks. Our algorithm receives any parameter value and returns: local minimum, second-order stationary point, or a strict descent direction. The presence of $M$ data points on the nondifferentiability of the ReLU divides the parameter space into at most $2^M$ regions, which makes analysis difficult. By exploiting polyhedral geometry, we reduce the total computation down to one convex quadratic program (QP) for each hidden node, $O(M)$ (in)equality tests, and one (or a few) nonconvex QP. For the last QP, we show that our specific problem can be solved efficiently, in spite of nonconvexity. In the benign case, we solve one equality constrained QP, and we prove that projected gradient descent solves it exponentially fast. In the bad case, we have to solve a few more inequality constrained QPs, but we prove that the time complexity is exponential only in the number of inequality constraints. Our experiments show that either benign case or bad case with very few inequality constraints occurs, implying that our algorithm is efficient in most cases.

📄 PDF Abstract BibTeX arXiv:1809.10858

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…

Similar Papers 제목 키워드 기반

Escaping Saddle Points for Nonsmooth Weakly Convex Functions via Perturbed Proximal Algorithms

2021-02-04 · Minhui Huang

We propose perturbed proximal algorithms that can provably escape strict saddles for nonsmooth weakly convex functions. The main results are based on a novel characterization of $\epsilon$-approximate local minimum for n…

HOUDINI: Escaping from Moderately Constrained Saddles

2022-05-27 · Dmitrii Avdiukhin, Grigory Yaroslavtsev

We give the first polynomial time algorithms for escaping from high-dimensional saddle points under a moderate number of constraints. Given gradient access to a smooth function $f \colon \mathbb R^d \to \mathbb R$ we sho…

Open-Ended Question Answering

Escaping Saddle Points with Bias-Variance Reduced Local Perturbed SGD for Communication Efficient Nonconvex Distributed Learning

2022-02-12 · Tomoya Murata, Taiji Suzuki

In recent centralized nonconvex distributed learning and federated learning, local methods are one of the promising approaches to reduce communication time. However, existing work has mainly focused on studying first-ord…

Distributed OptimizationFederated Learning

SSE-SAM: Balancing Head and Tail Classes Gradually through Stage-Wise SAM

2024-12-18 · Xingyu Lyu, Qianqian Xu, Zhiyong Yang, Shaojie Lyu 외

Real-world datasets often exhibit a long-tailed distribution, where vast majority of classes known as tail classes have only few samples. Traditional methods tend to overfit on these tail classes. Recently, a new approac…

Escaping Saddles with Stochastic Gradients

2018-03-15 · ICML 2018 7 · Hadi Daneshmand, Jonas Kohler, Aurelien Lucchi, Thomas Hofmann

We analyze the variance of stochastic gradients along negative curvature directions in certain non-convex machine learning models and show that stochastic gradients exhibit a strong component along these directions. Furt…