Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..
Online Learning of Neural Networks
Authors: Amit Daniely, Idan Mehalel, Elchanan Mossel
NeurIPS 2025 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | We study online learning of feedforward neural networks with the sign activation function that implement functions from the unit ball in Rd to a finite label set Y = {1, . . . , Y }. First, we characterize a margin condition that is sufficient and in some cases necessary for online learnability of a neural network: Every neuron in the first hidden layer classifies all instances with some margin γ bounded away from zero. Quantitatively, we prove that for any net, the optimal mistake bound is at most approximately TS(d, γ), which is the (d, γ)-totally-separable-packing number, a more restricted variation of the standard (d, γ)-packing number. We complement this result by constructing a net on which any learner makes TS(d, γ) many mistakes. We also give a quantitative lower bound of approximately TS(d, γ) max{1/(γd)d, d} when γ 1/2, implying that for some nets and input sequences every learner will err for exp(d) many times, and that a dimension-free mistake bound is almost always impossible. |
| Researcher Affiliation | Academia | Amit Daniely The Hebre University EMAIL Idan Mehalel The Hebrew University EMAIL Elchanan Mossel EMAIL |
| Pseudocode | Yes | Figure 1: The multiclass weighted majority algorithm. Figure 2: A perceptron with updates given by the manual" vector p. Figure 3: An expert parametrized by a sequence of neurons. Figure 4: An adaptive algorithm. |
| Open Source Code | No | Question: Does the paper provide open access to the data and code, with sufficient instructions to faithfully reproduce the main experimental results, as described in supplemental material? Answer: [NA] Justification: Theory paper. |
| Open Datasets | No | Question: Does the paper provide open access to the data and code, with sufficient instructions to faithfully reproduce the main experimental results, as described in supplemental material? Answer: [NA] Justification: Theory paper. |
| Dataset Splits | No | Question: Does the paper specify all the training and test details (e.g., data splits, hyperparameters, how they were chosen, type of optimizer, etc.) necessary to understand the results? Answer: [NA] Justification: Theory paper. |
| Hardware Specification | No | Question: For each experiment, does the paper provide sufficient information on the computer resources (type of compute workers, memory, time of execution) needed to reproduce the experiments? Answer: [NA] Justification: Theory paper. |
| Software Dependencies | No | Question: Does the paper specify all the training and test details (e.g., data splits, hyperparameters, how they were chosen, type of optimizer, etc.) necessary to understand the results? Answer: [NA] Justification: Theory paper. |
| Experiment Setup | No | Question: Does the paper specify all the training and test details (e.g., data splits, hyperparameters, how they were chosen, type of optimizer, etc.) necessary to understand the results? Answer: [NA] Justification: Theory paper. |