This paper develops local certificates for population-risk increments around a current model.

This paper shows that memorization in diffusion models is governed by local data coverage and derives a theoretical criterion to predict memorized samples.

This paper proposes a compression scheme for transmitting sparse local updates in distributed learning systems, and provides a converse based on f-divergence to characterize the communication-accuracy…

The authors extend the LOCAL model to unbounded degree graphs using Presburger monadic second-order (PMSO) formulas.

This paper systematically analyzes the forensic artifacts left by popular local LLM runners (Ollama, LM Studio, llama.cpp) on Windows and Linux, providing a foundational corpus of evidence for digital…

This paper presents a local computation algorithm to approximate the top eigenvector of a symmetric matrix with entries between -1 and 1, building on Swartworth and Woodruff's work.

This paper proves the conjecture that Local SGD outperforms Mini-batch SGD under bounded second-order heterogeneity for general convex objectives, improving the convergence guarantee and lower bounds.

This paper evaluates the performance of Da Gou Gun Optimization (DGO) on various optimization problems.

This paper studies how transformers exploit task-relevant structure in geometrically heterogeneous data and provides a new estimator and generalization bound for in-context learning.

This paper introduces a local information-operator framework to analyze spatial identifiability in inverse problems where spatially varying fields are inferred from heterogeneous observations.

This paper explores the capabilities and limitations of local search on the vertex coloring problem and introduces a new mutation operator that improves run time.

The paper establishes conditions for QUBO formulations of combinatorial optimization problems that guarantee valid binary and feasible local minimizers using gradient-based methods.

This paper adapts the distributed triangle-free coloring algorithm of Pettie and Su to solve LLL instances in logarithmic rounds, eliminating the LLL steps as the bottleneck.

The paper introduces Sharper Transductive Local Complexity (STLC), a localized complexity method for transductive learning that achieves the standard inductive rate and matches the transductive minima…