Feed-Forward Optimization With Delayed Feedback for Neural Networks
Backpropagation has long been criticized for being biologically implausible, relying on concepts that are not viable in natural learning processes. This paper proposes an alternative approach to solve two core issues, i.e., weight transport and update locking, for biological plausibility and computational efficiency. We introduce Feed-Forward with delayed Feedback (F$^3$), which improves upon prior work by utilizing delayed error information as a sample-wise scaling factor to approximate gradients more accurately. We find that F$^3$ reduces the gap in predictive performance between biologically plausible training algorithms and backpropagation by up to 96%. This demonstrates the applicability of biologically plausible training and opens up promising new avenues for low-energy training and parallelization.
Code (1)
Tasks
Biologically-plausible TrainingComputational EfficiencySimilar Papers 제목 키워드 기반
Bayesian Optimization under Stochastic Delayed Feedback
Bayesian optimization (BO) is a widely-used sequential method for zeroth-order optimization of complex and expensive-to-compute black-box functions. The existing BO methods assume that the function evaluation (feedback) …
Bayesian OptimizationCapacity-Constrained Online Convex Optimization with Delayed Feedback
Online learning with delayed feedback typically assumes that the learner can track all pending rounds until their feedback arrives. In practice, tracking resources are finite, and feedback from untracked rounds is perman…
Procrastinated Tree Search: Black-box Optimization with Delayed, Noisy, and Multi-Fidelity Feedback
In black-box optimization problems, we aim to maximize an unknown objective function, where the function is only accessible through feedbacks of an evaluation or simulation oracle. In real-life, the feedbacks of such ora…
Best arm identification in multi-armed bandits with delayed feedback
We propose a generalization of the best arm identification problem in stochastic multi-armed bandits (MAB) to the setting where every pull of an arm is associated with delayed feedback. The delay in feedback increases th…
Hyperparameter OptimizationMulti-Armed BanditsOnline Learning with Adversarial Delays
We study the performance of standard online learning algorithms when the feedback is delayed by an adversary. We show that \texttt{online-gradient-descent} and \texttt{follow-the-perturbed-leader} achieve regret $O(\sqrt…