Leveraging the two-timescale regime to demonstrate convergence of neural networks
We study the training dynamics of shallow neural networks, in a two-timescale regime in which the stepsizes for the inner layer are much smaller than those for the outer layer. In this regime, we prove convergence of the gradient flow to a global optimum of the non-convex optimization problem in a simple univariate setting. The number of neurons need not be asymptotically large for our result to hold, distinguishing our result from popular recent approaches such as the neural tangent kernel or mean-field regimes. Experimental illustration is provided, showing that the stochastic gradient descent behaves according to our description of the gradient flow and thus converges to a global optimum in the two-timescale regime, but can fail outside of this regime.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Leveraging the two timescale regime to demonstrate convergence of neural networks
We study the training dynamics of shallow neural networks, in a two-timescale regime in which the stepsizes for the inner layer are much smaller than those for the outer layer. In this regime, we prove convergence of the…
Vocal Bursts Valence PredictionConvergence of two-timescale gradient descent ascent dynamics: finite-dimensional and mean-field perspectives
The two-timescale gradient descent-ascent (GDA) is a canonical gradient algorithm designed to find Nash equilibria in min-max games. We analyze the two-timescale GDA by investigating the effects of learning rate ratios o…
A fast randomized incremental gradient method for decentralized non-convex optimization
We study decentralized non-convex finite-sum minimization problems described over a network of nodes, where each node possesses a local batch of data samples. In this context, we analyze a single-timescale randomized inc…
Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime
We study the convergence of gradient methods for the training of mean-field single hidden layer neural networks with square loss. Observing this is a separable non-linear least-square problem which is linear w.r.t. the o…
Convergence of Two-Timescale Markovian Stochastic Approximations with Applications in Reinforcement Learning
This work studies the convergence of two-timescale stochastic approximations (SA), a class of iterative algorithms that update two sets of parameters in fast and slow timescales respectively. Notable examples of two-time…
Reinforcement Learning