conftrace_
← Optimization & Theory
Machine Learning › Optimization & Theory ›

Neural Network Optimization

3,648 papers

Papers per year

Papers

A Variant of Anderson Mixing with Minimal Memory Size NIPS 2022
Invertible Monotone Operators for Normalizing Flows NIPS 2022
The Curse of Unrolling: Rate of Differentiating Through Optimization NIPS 2022
On the non-universality of deep learning: quantifying the cost of symmetry NIPS 2022
Parameters or Privacy: A Provable Tradeoff Between Overparameterization and Membership Inference NIPS 2022
Biologically-plausible backpropagation through arbitrary timespans via local neuromodulators NIPS 2022
The Role of Baselines in Policy Gradient Optimization NIPS 2022
SAPipe: Staleness-Aware Pipeline for Data Parallel DNN Training NIPS 2022
Escaping from the Barren Plateau via Gaussian Initializations in Deep Variational Quantum Circuits NIPS 2022
Large-batch Optimization for Dense Visual Predictions: Training Faster R-CNN in 4.2 Minutes NIPS 2022
Most Activation Functions Can Win the Lottery Without Excessive Depth NIPS 2022
Towards Theoretically Inspired Neural Initialization Optimization NIPS 2022
Theoretically Provable Spiking Neural Networks NIPS 2022
Understanding Deep Contrastive Learning via Coordinate-wise Optimization NIPS 2022
Surprising Instabilities in Training Deep Networks and a Theoretical Analysis NIPS 2022
Finite-Time Analysis of Adaptive Temporal Difference Learning with Deep Neural Networks NIPS 2022
Benign Underfitting of Stochastic Gradient Descent NIPS 2022
Gradient flow dynamics of shallow ReLU networks for square loss and orthogonal inputs NIPS 2022
Instability and Local Minima in GAN Training with Kernel Discriminators NIPS 2022
Optimal and Adaptive Monteiro-Svaiter Acceleration NIPS 2022
Hidden Progress in Deep Learning: SGD Learns Parities Near the Computational Limit NIPS 2022
An In-depth Study of Stochastic Backpropagation NIPS 2022
To update or not to update? Neurons at equilibrium in deep models NIPS 2022
A Combinatorial Perspective on the Optimization of Shallow ReLU Networks NIPS 2022
On-Device Training Under 256KB Memory NIPS 2022