paper-with-me

Papers

Gradient descent in some simple settings

2018-08-14 · Y. Cooper

In this note, we observe the behavior of gradient flow and discrete and noisy gradient descent in some simple settings. It is commonly noted that addition of noise to gradient descent can affect the trajectory of gradient descent. Here, we run some computer experiments for gradient descent on some simple functions, and observe this principle in some concrete examples.

📄 PDF Abstract BibTeX arXiv:1808.04839

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Potential-Function Proofs for First-Order Methods

2017-12-13 · Nikhil Bansal, Anupam Gupta

This note discusses proofs for convergence of first-order methods based on simple potential-function arguments. We cover methods like gradient descent (for both smooth and non-smooth settings), mirror descent, and some a…

Last-iterate convergence rates for min-max optimization

2019-06-05 · ICLR 2020 1 · Jacob Abernethy, Kevin A. Lai, Andre Wibisono

While classic work in convex-concave min-max optimization relies on average-iterate convergence results, the emergence of nonconvex applications such as training Generative Adversarial Networks has led to renewed interes…

On the Computational Power of Online Gradient Descent

2018-07-03 · Vaggos Chatziafratis, Tim Roughgarden, Joshua R. Wang

We prove that the evolution of weight vectors in online gradient descent can encode arbitrary polynomial-space computations, even in very simple learning settings. Our results imply that, under weak complexity-theoretic …

Convergence Analysis of Fractional Gradient Descent

2023-11-30 · Ashwani Aggarwal

Fractional derivatives are a well-studied generalization of integer order derivatives. Naturally, for optimization, it is of interest to understand the convergence properties of gradient descent using fractional derivati…

Structured second-order methods via natural gradient descent

2021-07-22 · Wu Lin, Frank Nielsen, Mohammad Emtiyaz Khan, Mark Schmidt

In this paper, we propose new structured second-order methods and structured adaptive-gradient methods obtained by performing natural-gradient descent on structured parameter spaces. Natural-gradient descent is an attrac…

Second-order methods