Low-Dimension-to-High-Dimension Generalization And Its Implications for Length Generalizationby Yang Chen, Yitao Liang, Zhouchen LinFirst submitted…
Towards Sharper Risk Bounds for Minimax Problemsby Bowei Zhu, Shaojie Li, Yong LiuFirst submitted to…
Randomized Asymmetric Chain of LoRA: The First Meaningful Theoretical Framework for Low-Rank Adaptationby Grigory Malinovsky,…
On the Convergence of (Stochastic) Gradient Descent for Kolmogorov–Arnold Networksby Yihang Gao, Vincent Y. F.…
Generalization Bounds and Model Complexity for Kolmogorov-Arnold Networksby Xianyang Zhang, Huijuan ZhouFirst submitted to arxiv…
Noise is All You Need: Private Second-Order Convergence of Noisy SGDby Dmitrii Avdiukhin, Michael Dinitz,…
Addax: Utilizing Zeroth-Order Gradients to Improve Memory Efficiency and Performance of SGD for Fine-Tuning Language…
Extended convexity and smoothness and their applications in deep learningby Binchuan Qi, Wei Gong, Li…
Improving Distribution Alignment with Diversity-based Samplingby Andrea Napoli, Paul WhiteFirst submitted to arxiv on: 5…
SGD with memory: fundamental properties and stochastic accelerationby Dmitry Yarotsky, Maksim VelikanovFirst submitted to arxiv…