pith. sign in

arxiv: 1605.08361 · v2 · pith:VUYQU7AUnew · submitted 2016-05-26 · 📊 stat.ML · cs.LG· cs.NE

No bad local minima: Data independent training error guarantees for multilayer neural networks

classification 📊 stat.ML cs.LGcs.NE
keywords localtrainingguaranteeslossmnnsdatadifferentiableerror
0
0 comments X
read the original abstract

We use smoothed analysis techniques to provide guarantees on the training loss of Multilayer Neural Networks (MNNs) at differentiable local minima. Specifically, we examine MNNs with piecewise linear activation functions, quadratic loss and a single output, under mild over-parametrization. We prove that for a MNN with one hidden layer, the training error is zero at every differentiable local minimum, for almost every dataset and dropout-like noise realization. We then extend these results to the case of more than one hidden layer. Our theoretical guarantees assume essentially nothing on the training data, and are verified numerically. These results suggest why the highly non-convex loss of such MNNs can be easily optimized using local updates (e.g., stochastic gradient descent), as observed empirically.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Flat Channels to Infinity in Neural Loss Landscapes

    cs.LG 2025-06 unverdicted novelty 7.0

    Neural loss landscapes contain flat channels to infinity along which gradient flow leads pairs of neurons to implement gated linear units.

  2. Weight-space symmetry in deep networks gives rise to permutation saddles, connected by equal-loss valleys across the loss landscape

    cs.LG 2019-07 conditional novelty 7.0

    Permutation symmetries generate permutation saddles and equal-loss valleys linking equivalent global minima, yielding a lower bound on symmetry-induced critical points.

  3. Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models

    cs.LG 2024-01 unverdicted novelty 6.0

    SPIN lets weak LLMs become strong by self-generating training data from previous model versions and training to prefer human-annotated responses over its own outputs, outperforming DPO even with extra GPT-4 data on be...

  4. Robust and Resource Efficient Identification of Two Hidden Layer Neural Networks

    cs.LG 2019-06 unverdicted novelty 6.0

    Presents an active-sampling method that approximates the weight subspace from Hessian finite differences, recovers the rank-1 tensors by robust nonlinear programming, and attributes layers with gradient descent, yield...

  5. On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima

    cs.LG 2016-09 unverdicted novelty 6.0

    Large-batch methods converge to sharp minima causing a generalization gap, while small-batch methods reach flat minima due to inherent gradient noise.