3 papers
stat.ML2026
How Does the ReLU Activation Affect the Implicit Bias of Gradient Descent on High-dimensional Neural Network Regression?
Kuo-Wei Lai, Guanghui Wang, Molei Tao +1
Overparameterized ML models, including neural networks, typically induce underdetermined training objectives with multiple global minima. The implicit bias refers to the limiting g…
cs.LG2026
The Bridge-Garden Dilemma in LLM Distillation: Why Mixing Hard and Soft Labels Works
Guanghui Wang, Kaiwen Lv Kacuila, Zhiyong Yang +5
Knowledge distillation (KD) transfers knowledge from a large teacher model to a smaller student. In language modeling, the student is trained either on tokens sampled from the teac…
cs.LG2026
Thin Keys, Full Values: Reducing KV Cache via Low-Dimensional Attention Selection
Hengshuai Yao, Xing Chen, Ahmed Murtadha +1
Standard Transformer attention uses identical dimensionality for queries, keys, and values, yet these components serve different roles: queries and keys produce scalar attention we…