会员服务
ADP-VRSGP: Decentralized Learning with Adaptive Differential Privacy via Variance-Reduced Stochastic Gradient Push
Arxiv
0+阅读 · 10月23日
MILES: Modality-Informed Learning Rate Scheduler for Balancing Multimodal Learning
Arxiv
0+阅读 · 10月20日
Seesaw: Accelerating Training by Balancing Learning Rate and Batch Size Scheduling
Arxiv
0+阅读 · 10月16日
Scale-Invariant Regret Matching and Online Learning with Optimal Convergence: Bridging Theory and Practice in Zero-Sum Games
Arxiv
0+阅读 · 10月13日
Tight Regret Upper and Lower Bounds for Optimistic Hedge in Two-Player Zero-Sum Games
Arxiv
0+阅读 · 10月13日
AutoGD: Automatic Learning Rate Selection for Gradient Descent
Arxiv
0+阅读 · 10月10日
Faster Convergence of Riemannian Stochastic Gradient Descent with Increasing Batch Size
Arxiv
0+阅读 · 10月13日
Convergence of two-timescale gradient descent ascent dynamics: finite-dimensional and mean-field perspectives
Arxiv
0+阅读 · 10月10日
Dynamic Learning Rate for Deep Reinforcement Learning: A Bandit Approach
Arxiv
0+阅读 · 10月8日
Exact and Linear Convergence for Federated Learning under Arbitrary Client Participation is Attainable
Arxiv
0+阅读 · 10月5日
Scale-Invariant Regret Matching and Online Learning with Optimal Convergence: Bridging Theory and Practice in Zero-Sum Games
Arxiv
0+阅读 · 10月6日
Arithmetic-Mean $μ$P for Modern Architectures: A Unified Learning-Rate Scale for CNNs and ResNets
Arxiv
0+阅读 · 10月5日
Why Do We Need Warm-up? A Theoretical Perspective
Why Do We Need Warm-up? A Theoretical Perspective
Arxiv
0+阅读 · 10月3日
Faster Convergence of Riemannian Stochastic Gradient Descent with Increasing Batch Size
Arxiv
0+阅读 · 9月27日
Unveiling the Role of Learning Rate Schedules via Functional Scaling Laws
Arxiv
0+阅读 · 9月24日
参考链接
微信扫码咨询专知VIP会员
Top