Tag
This blog post discusses a viral paper showing that LLM embeddings of months project to a circle in PCA space with circulant Gram matrices, and describes an experiment to find random-seeming words that exhibit similar geometric properties.
This paper presents improved algorithms for learning truncated Boolean product distributions, achieving sample complexity that matches the untruncated minimax rate using the concept of influence from Boolean function analysis.
This paper develops a precise theoretical characterization of the empirical risk landscape for multi-index models in high dimensions, proposing an incremental approximate message passing (IAMP) algorithm that achieves near-optimal performance among polynomial-time methods, using concepts from statistical physics such as replica symmetry breaking.
This paper presents exact dimensionality reductions using Schur complement and Sylvester's determinant identity to reduce computational complexity from O(N^3) to O(k^3+N^2k) per step for non-smooth NML estimation, achieving over 14,000x speedup while maintaining numerical precision.
This paper provides the first non-asymptotic sample complexity bounds for learning exponential families of polynomials with score matching, showing polynomial dependence on model dimension.