会员服务
Generalized Posterior Calibration via Sequential Monte Carlo Sampler
Arxiv
0+阅读 · 4月25日
Key ingredients for effective zero-shot cross-lingual knowledge transfer in generative tasks
Arxiv
0+阅读 · 4月22日
Neural Optimizer Equation, Decay Function, and Learning Rate Schedule Joint Evolution
Arxiv
0+阅读 · 4月10日
FedAgg: Adaptive Federated Learning with Aggregated Gradients
Arxiv
0+阅读 · 4月12日
Adaptive Federated Learning via New Entropy Approach
Arxiv
0+阅读 · 4月12日
Improving Line Search Methods for Large Scale Neural Network Training
Arxiv
0+阅读 · 3月27日
Prodigy: An Expeditiously Adaptive Parameter-Free Learner
Arxiv
0+阅读 · 3月19日
Adaptive Learning Rate for Follow-the-Regularized-Leader: Competitive Analysis and Best-of-Both-Worlds
Arxiv
0+阅读 · 3月10日
Tune without Validation: Searching for Learning Rate and Weight Decay on Training Sets
Arxiv
0+阅读 · 3月8日
Adaptive Learning Rate for Follow-the-Regularized-Leader: Competitive Ratio Analysis and Best-of-Both-Worlds
Arxiv
0+阅读 · 3月1日
Masks, Signs, And Learning Rate Rewinding
Arxiv
0+阅读 · 2月29日
Why do Learning Rates Transfer? Reconciling Optimization and Scaling Limits for Deep Learning
Arxiv
0+阅读 · 2月27日
Non-ergodic linear convergence property of the delayed gradient descent under the strongly convexity and the Polyak-Łojasiewicz condition
Arxiv
0+阅读 · 2月22日
Rotational Equilibrium: How Weight Decay Balances Learning Across Neural Networks
Arxiv
0+阅读 · 2月21日
Robust Learning Rate Selection for Stochastic Optimization via Splitting Diagnostic
Arxiv
0+阅读 · 2月17日
参考链接
微信扫码咨询专知VIP会员
Top