3 papers
cs.LG2025
Approximate Replicability in Learning
Max Hopkins, Russell Impagliazzo, Christopher Ye
Replicability, introduced by (Impagliazzo et al. STOC '22), is the notion that algorithms should remain stable under a resampling of their inputs (given access to shared randomness…
cs.CC2024
The Computational Complexity of Factored Graphs
Shreya Gupta, Boyang Huang, Russell Impagliazzo +2
While graphs and abstract data structures can be large and complex, practical instances are often regular or highly structured. If the instance has sufficient structure, we might h…
stat.ML2024
Replicability in High Dimensional Statistics
Max Hopkins, Russell Impagliazzo, Daniel Kane +2
The replicability crisis is a major issue across nearly all areas of empirical science, calling for the formal study of replicability in statistics. Motivated in this context, [Imp…