paper-with-me

Papers

Neural Teleportation

2020-12-02 · Marco Armenta, Thierry Judge, Nathan Painchaud, Youssef Skandarani, Carl Lemaire, Gabriel Gibeau Sanchez, Philippe Spino, Pierre-Marc Jodoin

In this paper, we explore a process called neural teleportation, a mathematical consequence of applying quiver representation theory to neural networks. Neural teleportation "teleports" a network to a new position in the weight space and preserves its function. This phenomenon comes directly from the definitions of representation theory applied to neural networks and it turns out to be a very simple operation that has remarkable properties. We shed light on surprising and counter-intuitive consequences neural teleportation has on the loss landscape. In particular, we show that teleportation can be used to explore loss level curves, that it changes the local loss landscape, sharpens global minima and boosts back-propagated gradients at any moment during the learning process. Our results can be reproduced with the code available here: https://github.com/vitalab/neuralteleportation

📄 PDF Abstract BibTeX arXiv:2012.01118

Code (1)

vitalab/neuralteleportation 공식 구현 pytorch

Tasks

Position

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

Level Set Teleportation: An Optimization Perspective

2024-03-05 · Aaron Mishkin, Alberto Bietti, Robert M. Gower

We study level set teleportation, an optimization routine which tries to accelerate gradient descent (GD) by maximizing the gradient norm over a level set of the objective. While teleportation intuitively speeds-up GD vi…

LEMMA

Symmetry Teleportation for Accelerated Optimization

2022-05-21 · Bo Zhao, Nima Dehmamy, Robin Walters, Rose Yu

Existing gradient-based optimization methods update parameters locally, in a direction that minimizes the loss function. We study a different approach, symmetry teleportation, that allows parameters to travel a large dis…

Second-order methods

Random Surfing Without Teleportation

2015-05-30 · Athanasios N. Nikolakopoulos, John D. Garofalakis

In the standard Random Surfer Model, the teleportation matrix is necessary to ensure that the final PageRank vector is well-defined. The introduction of this matrix, however, results in serious problems and imposes funda…

Teleportation With Null Space Gradient Projection for Optimization Acceleration

2025-02-17 · Zihao Wu, Juncheng Dong, Ahmed Aloui, Vahid Tarokh

Optimization techniques have become increasingly critical due to the ever-growing model complexity and data scale. In particular, teleportation has emerged as a promising approach, which accelerates convergence of gradie…

Improving Convergence and Generalization Using Parameter Symmetries

2023-05-22 · Bo Zhao, Robert M. Gower, Robin Walters, Rose Yu

In many neural networks, different values of the parameters may result in the same loss value. Parameter space symmetries are loss-invariant transformations that change the model parameters. Teleportation applies such tr…

Meta-Learning