paper-with-me

홈 › Papers

Lyapunov Exponents for Diversity in Differentiable Games

2021-12-24 · Jonathan Lorraine, Paul Vicol, Jack Parker-Holder, Tal Kachman, Luke Metz, Jakob Foerster

Ridge Rider (RR) is an algorithm for finding diverse solutions to optimization problems by following eigenvectors of the Hessian ("ridges"). RR is designed for conservative gradient systems (i.e., settings involving a single loss function), where it branches at saddles - easy-to-find bifurcation points. We generalize this idea to non-conservative, multi-agent gradient systems by proposing a method - denoted Generalized Ridge Rider (GRR) - for finding arbitrary bifurcation points. We give theoretical motivation for our method by leveraging machinery from the field of dynamical systems. We construct novel toy problems where we can visualize new phenomena while giving insight into high-dimensional problems of interest. Finally, we empirically evaluate our method by finding diverse solutions in the iterated prisoners' dilemma and relevant machine learning problems including generative adversarial networks.

📄 PDF Abstract BibTeX arXiv:2112.14570

Code (0)

등록된 구현이 없습니다.

Tasks

Diversity

Similar Papers 제목 키워드 기반

Gradient Flossing: Improving Gradient Descent through Dynamic Control of Jacobians

2023-12-28 · NeurIPS 2023 11 · Rainer Engelken

Training recurrent neural networks (RNNs) remains a challenge due to the instability of gradients across long time horizons, which can lead to exploding and vanishing gradients. Recent research has linked these problems …

Utilizing Lyapunov Exponents in designing deep neural networks

2024-10-08 · Tirthankar Mittra

Training large deep neural networks is resource intensive. This study investigates whether Lyapunov exponents can accelerate this process by aiding in the selection of hyperparameters. To study this I formulate an optimi…

Tracking Finite-Time Lyapunov Exponents to Robustify Neural ODEs

2026-02-10 · Tobias Wöhrer, Christian Kuehn arxiv

We investigate finite-time Lyapunov exponents (FTLEs), a measure for exponential separation of input perturbations, of deep neural networks within the framework of continuous-depth neural ODEs. We demonstrate that FTLEs …

On Lyapunov exponents and adversarial perturbation

2018-02-20 · Vinay Uday Prabhu, Nishant Desai, John Whaley

In this paper, we would like to disseminate a serendipitous discovery involving Lyapunov exponents of a 1-D time series and their use in serving as a filtering defense tool against a specific kind of deep adversarial per…

Time SeriesTime Series Analysis

Finite-time Lyapunov exponents of deep neural networks

2023-06-21 · L. Storm, H. Linander, J. Bec, K. Gustavsson 외

We compute how small input perturbations affect the output of deep neural networks, exploring an analogy between deep networks and dynamical systems, where the growth or decay of local perturbations is characterised by f…