paper-with-me

홈 › Papers

The committee machine: Computational to statistical gaps in learning a two-layers neural network

2018-06-14 · NeurIPS 2018 12 · Benjamin Aubin, Antoine Maillard, Jean Barbier, Florent Krzakala, Nicolas Macris, Lenka Zdeborová

Heuristic tools from statistical physics have been used in the past to locate the phase transitions and compute the optimal learning and generalization errors in the teacher-student scenario in multi-layer neural networks. In this contribution, we provide a rigorous justification of these approaches for a two-layers neural network model called the committee machine. We also introduce a version of the approximate message passing (AMP) algorithm for the committee machine that allows to perform optimal learning in polynomial time for a large set of parameters. We find that there are regimes in which a low generalization error is information-theoretically achievable while the AMP algorithm fails to deliver it, strongly suggesting that no efficient algorithm exists for those cases, and unveiling a large computational gap.

📄 PDF Abstract BibTeX arXiv:1806.05451

Code (1)

benjaminaubin/TheCommitteeMachine 공식 구현

Similar Papers 제목 키워드 기반

Statistical mechanics of extensive-width Bayesian neural networks near interpolation

2025-05-30 · Jean Barbier, Francesco Camilli, Minh-Toan Nguyen, Mauro Pastore 외

For three decades statistical mechanics has been providing a framework to analyse neural networks. However, the theoretically tractable models, e.g., perceptrons, random features models and kernel machines, or multi-inde…

A Noise Sensitivity Exponent Controls Large Statistical-to-Computational Gaps in Single- and Multi-Index Models

2026-03-18 · Leonardo Defilippis, Florent Krzakala, Bruno Loureiro, Antoine Maillard arxiv

Understanding when learning is statistically possible yet computationally hard is a central challenge in high-dimensional statistics. In this work, we investigate this question in the context of single- and multi-index m…

Bridging Smart Meter Gaps: A Benchmark of Statistical, Machine Learning and Time Series Foundation Models for Data Imputation

2025-01-13 · Amir Sartipi, Joaquin Delgado Fernandez, Sergio Potenciano Menci, Alessio Magitteri

The integrity of time series data in smart grids is often compromised by missing values due to sensor failures, transmission errors, or disruptions. Gaps in smart meter data can bias consumption analyses and hinder relia…

ImputationMissing ValuesTime Series

Notes on computational-to-statistical gaps: predictions using statistical physics

2018-03-29 · Afonso S. Bandeira, Amelia Perry, Alexander S. Wein

In these notes we describe heuristics to predict computational-to-statistical gaps in certain statistical problems. These are regimes in which the underlying statistical problem is information-theoretically possible alth…

Proof-of-Useful-Work as Dual-Purpose Mechanism for Blockchain and AI: Blockchain Consensus that Enables Privacy Preserving Data Mining

2019-07-20 · Hjalmar Turesson, Henry M. Kim, Marek Laskowski, Alexandra Roatis

Blockchains rely on a consensus among participants to achieve decentralization and security. However, reaching consensus in an online, digital world where identities are not tied to physical users is a challenging proble…

Privacy Preserving