会员服务
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
Unveiling the Role of Learning Rate Schedules via Functional Scaling Laws
Arxiv
0+阅读 · 9月23日
Theoretical Analysis on how Learning Rate Warmup Accelerates Convergence
Arxiv
0+阅读 · 9月9日
Purifying Shampoo: Investigating Shampoo's Heuristics by Decomposing its Preconditioner
Arxiv
0+阅读 · 6月4日
Faster Rates for No-Regret Learning in General Games via Cautious Optimism
Arxiv
0+阅读 · 3月31日
Benefits of Learning Rate Annealing for Tuning-Robustness in Stochastic Optimization
Arxiv
0+阅读 · 3月12日
Towards hyperparameter-free optimization with differential privacy
Arxiv
0+阅读 · 3月2日
Gaussian On-the-Fly Splatting: A Progressive Framework for Robust Near Real-Time 3DGS Optimization
Arxiv
0+阅读 · 3月17日
Beyond Cosine Decay: On the effectiveness of Infinite Learning Rate Schedule for Continual Pre-training
Arxiv
0+阅读 · 3月4日
A Multi-Power Law for Loss Curve Prediction Across Learning Rate Schedules
Arxiv
0+阅读 · 3月17日
Mowgli: Passively Learned Rate Control for Real-Time Video
Arxiv
0+阅读 · 3月18日
Straight to Zero: Why Linearly Decaying the Learning Rate to Zero Works Best for LLMs
Arxiv
0+阅读 · 2月21日
Exploring Learning Rate Selection in Generalised Bayesian Inference using Posterior Predictive Checks
Arxiv
0+阅读 · 1月21日
Greedy Stein Variational Gradient Descent: An algorithmic approach for wave prospection problems
Arxiv
0+阅读 · 1月31日
参考链接
微信扫码咨询专知VIP会员
Top