paper-with-me

Papers

Loss Landscape Sightseeing with Multi-Point Optimization

2019-10-09 · Ivan Skorokhodov, Mikhail Burtsev

We present multi-point optimization: an optimization technique that allows to train several models simultaneously without the need to keep the parameters of each one individually. The proposed method is used for a thorough empirical analysis of the loss landscape of neural networks. By extensive experiments on FashionMNIST and CIFAR10 datasets we demonstrate two things: 1) loss surface is surprisingly diverse and intricate in terms of landscape patterns it contains, and 2) adding batch normalization makes it more smooth. Source code to reproduce all the reported results is available on GitHub: https://github.com/universome/loss-patterns.

📄 PDF Abstract BibTeX arXiv:1910.03867

Code (1)

universome/loss-patterns 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

Batch Normalization 설명 없음

Similar Papers 제목 키워드 기반

A Deep Neural Network's Loss Surface Contains Every Low-dimensional Pattern

2019-12-16 · Wojciech Marian Czarnecki, Simon Osindero, Razvan Pascanu, Max Jaderberg

The work "Loss Landscape Sightseeing with Multi-Point Optimization" (Skorokhodov and Burtsev, 2019) demonstrated that one can empirically find arbitrary 2D binary patterns inside loss surfaces of popular neural networks.…

Affective Recommendation System for Tourists by Using Emotion Generating Calculations

2018-04-09 · Takumi Ichimura, Issei Tachibana

An emotion orientated intelligent interface consists of Emotion Generating Calculations (EGC) and Mental State Transition Network (MSTN). We have developed the Android EGC application software which the agent works to ev…

Landscape-Awareness for Geometric View Diffusion Model

2026-05-19 · Yan-Ting Chen, Hao-Wei Chen, Tsu-Ching Hsiao, Chun-Yi Lee arxiv

Accurate camera viewpoint estimation under sparse-view conditions remains challenging, particularly in two-view scenarios. Recent approaches leverage diffusion models such as Zero123 to synthesize novel views conditioned…

Embedding Principle of Loss Landscape of Deep Neural Networks

2021-05-30 · NeurIPS 2021 12 · Yaoyu Zhang, Zhongwang Zhang, Tao Luo, Zhi-Qin John Xu

Understanding the structure of loss landscape of deep neural networks (DNNs)is obviously important. In this work, we prove an embedding principle that the loss landscape of a DNN "contains" all the critical points of all…

Protein Folding

The loss landscape of deep linear neural networks: a second-order analysis

2021-07-28 · El Mehdi Achour, François Malgouyres, Sébastien Gerchinovitz

We study the optimization landscape of deep linear neural networks with the square loss. It is known that, under weak assumptions, there are no spurious local minima and no local maxima. However, the existence and divers…

Diversity