On the Optimization of Deep Networks: Implicit Acceleration by Overparameterization
read the original abstract
Conventional wisdom in deep learning states that increasing depth improves expressiveness but complicates optimization. This paper suggests that, sometimes, increasing depth can speed up optimization. The effect of depth on optimization is decoupled from expressiveness by focusing on settings where additional layers amount to overparameterization - linear neural networks, a well-studied model. Theoretical analysis, as well as experiments, show that here depth acts as a preconditioner which may accelerate convergence. Even on simple convex problems such as linear regression with $\ell_p$ loss, $p>2$, gradient descent can benefit from transitioning to a non-convex overparameterized objective, more than it would from some common acceleration schemes. We also prove that it is mathematically impossible to obtain the acceleration effect of overparametrization via gradients of any regularizer.
This paper has not been read by Pith yet.
Forward citations
Cited by 10 Pith papers
-
A Theory of Saddle Escape in Deep Nonlinear Networks
Derives exact Frobenius norm imbalance identity for deep nonlinear networks, classifies activations into four classes, and obtains critical-depth escape time law τ★ = Θ(ε^{-(r-2)}) from reduction to scalar ODE on perm...
-
Dead-Direction Conditioners: Gauge-Equivariant Preconditioning for Deep Networks
Dead-Direction Conditioners provide gauge-equivariant preconditioning by conditioning optimizer state on symmetry orbits, yielding improved resistance to over-training collapse and higher detection of dead directions ...
-
Estimating Implicit Regularization in Deep Learning
Gradient matching empirically recovers implicit regularization effects such as l2 penalties from early stopping and dropout in neural networks.
-
A Theory of Saddle Escape in Deep Nonlinear Networks
An exact norm-imbalance identity classifies activations into four classes and reduces deep nonlinear training flow to a scalar ODE that predicts saddle escape time scaling as ε to the power of minus (r-2) for r bottle...
-
A Theory of Saddle Escape in Deep Nonlinear Networks
Derives exact norm-imbalance identity for deep nonlinear nets, classifying activations into four classes and yielding escape time law τ★ = Θ(ε^{-(r-2)}) governed by bottleneck depth r.
-
Geometric and Spectral Alignment for Deep Neural Network II
The work establishes margin-verified certificates for physical alignment of residual Jacobian chains by bounding truncation errors and decomposing the Physical Alignment Matrix orthogonally under fitted effective-rank...
-
What Does Flow Matching Bring To TD Learning?
Flow matching critics outperform monolithic ones in RL by 2x performance and 5x sample efficiency via test-time error recovery through integration and multi-point velocity supervision that preserves feature plasticity.
-
GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding
GShard supplies automatic sharding and conditional computation support that enabled training a 600-billion-parameter multilingual translation model on thousands of TPUs with superior quality.
-
Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges
A single multilingual NMT model for 103 languages trained on 25B examples demonstrates transfer learning benefits for low-resource languages.
-
Hessian based analysis of SGD for Deep Nets: Dynamics and Generalization
Provides Hessian-based theoretical characterizations of SGD dynamics and a scale-invariant generalization bound for deep nets, backed by experiments on synthetic data, MNIST, and CIFAR-10.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.