paper-with-me

Papers

Complex energy landscapes in spiked-tensor and simple glassy models: ruggedness, arrangements of local minima and phase transitions

2018-04-08 · Valentina Ros, Gerard Ben Arous, Giulio Biroli, Chiara Cammarota

We study rough high-dimensional landscapes in which an increasingly stronger preference for a given configuration emerges. Such energy landscapes arise in glass physics and inference. In particular we focus on random Gaussian functions, and on the spiked-tensor model and generalizations. We thoroughly analyze the statistical properties of the corresponding landscapes and characterize the associated geometrical phase transitions. In order to perform our study, we develop a framework based on the Kac-Rice method that allows to compute the complexity of the landscape, i.e. the logarithm of the typical number of stationary points and their Hessian. This approach generalizes the one used to compute rigorously the annealed complexity of mean-field glass models. We discuss its advantages with respect to previous frameworks, in particular the thermodynamical replica method which is shown to lead to partially incorrect predictions.

📄 PDF Abstract BibTeX arXiv:1804.02686

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Computational Thresholds in Multi-Modal Learning via the Spiked Matrix-Tensor Model

2025-06-03 · Hugo Tabanelli, Pierre Mergny, Lenka Zdeborova, Florent Krzakala

We study the recovery of multiple high-dimensional signals from two noisy, correlated modalities: a spiked matrix and a spiked tensor sharing a common low-rank structure. This setting generalizes classical spiked matrix …

Who is Afraid of Big Bad Minima? Analysis of gradient-flow in spiked matrix-tensor models

2019-12-01 · NeurIPS 2019 12 · Stefano Sarao Mannelli, Giulio Biroli, Chiara Cammarota, Florent Krzakala 외

Gradient-based algorithms are effective for many machine learning tasks, but despite ample recent effort and some progress, it often remains unclear why they work in practice in optimising high-dimensional non-convex fun…

Who is Afraid of Big Bad Minima? Analysis of Gradient-Flow in a Spiked Matrix-Tensor Model

2019-07-18 · Stefano Sarao Mannelli, Giulio Biroli, Chiara Cammarota, Florent Krzakala 외

Gradient-based algorithms are effective for many machine learning tasks, but despite ample recent effort and some progress, it often remains unclear why they work in practice in optimising high-dimensional non-convex fun…

Analytical Study of Momentum-Based Acceleration Methods in Paradigmatic High-Dimensional Non-Convex Problems

2021-02-23 · NeurIPS 2021 12 · Stefano Sarao Mannelli, Pierfrancesco Urbani

The optimization step in many machine learning problems rarely relies on vanilla gradient descent but it is common practice to use momentum-based accelerated methods. Despite these algorithms being widely applied to arbi…

Numerical Integration

Large-N dynamics of the spiked tensor model with random initial conditions

2022-08-26 · Vasily Sazonov

In these notes, we develop a path integral approach for the partial differential equations with random initial conditions. Then, we apply it to the dynamics of the spiked tensor model and show that the large-$N$ saddle p…