Training Dynamics of Multi-Head Softmax Attention for In-Context Learning: Emergence, Convergence, and Optimalityby Siyu Chen,…
Lasso with Latents: Efficient Estimation, Covariate Rescaling, and Computational-Statistical Gapsby Jonathan Kelner, Frederic Koehler, Raghu…
Statistical Agnostic Regression: a machine learning method to validate regression modelsby Juan M Gorriz, J.…
In-Context Learning of a Linear Transformer Block: Benefits of the MLP Component and One-Step GD…
Multivariate Online Linear Regression for Hierarchical Forecastingby Massil Hihat, Guillaume Garrigos, Adeline Fermanian, Simon BussyFirst…
Sparse Linear Regression and Lattice Problemsby Aparna Gupte, Neekon Vafa, Vinod VaikuntanathanFirst submitted to arxiv…
Computational-Statistical Gaps for Improper Learning in Sparse Linear Regressionby Rares-Darius Buhai, Jingqiu Ding, Stefan TiegelFirst…
Linear Transformers are Versatile In-Context Learnersby Max Vladymyrov, Johannes von Oswald, Mark Sandler, Rong GeFirst…
Private Gradient Descent for Linear Regression: Tighter Error Bounds and Instance-Specific Uncertainty Estimationby Gavin Brown,…
Improved Indoor Localization with Machine Learning Techniques for IoT applicationsby M.W.P. MadurangaFirst submitted to arxiv…