9 citations · 14 across the 2 of their papers we have counts for
6 papers
Interpreting Neural Networks through the Polytope Lens
Sid Black, Lee Sharkey, Leo Grinsztajn +8
Mechanistic interpretability aims to explain what a neural network has learned at a nuts-and-bolts level. What are the fundamental primitives of neural network representations? Pre…
Scatterbrain: Unifying Sparse and Low-rank Attention Approximation
Beidi Chen, Tri Dao, Eric Winsor +3
Recent advances in efficient Transformers have exploited either the sparsity or low-rank properties of attention matrices to reduce the computational and memory bottlenecks of mode…
Generalized Lyndon Factorizations of Infinite Words
Amanda Burcroff, Eric Winsor
A generalized lexicographic order on words is a lexicographic order where the total order of the alphabet depends on the position of the comparison. A generalized Lyndon word is a…
A Refined Conjecture for the Variance of Gaussian Primes Across Sectors
Ryan C. Chen, Yujin H. Kim, Jared D. Lichtman +6
We derive a refined conjecture for the variance of Gaussian primes across sectors, with a power saving error term, by applying the L-functions Ratios Conjecture. We observe a bifur…
Limiting Distributions in Generalized Zeckendorf Decompositions
Alexandre Gueganic, Granger Carty, Yujin H. Kim +5
An equivalent definition of the Fibonacci numbers is that they are the unique sequence such that every integer can be written uniquely as a sum of non-adjacent terms. We can view t…
Spectral Statistics of Non-Hermitian Random Matrix Ensembles
Ryan C. Chen, Yujin H. Kim, Jared D. Lichtman +3
Recently Burkhardt et. al. introduced the -checkerboard random matrix ensembles, which have a split limiting behavior of the eigenvalues (in the limit all but of the eigenva…