2 papers
math.OC2026
Stochastic Decentralized Optimization of Non-Smooth Convex and Convex-Concave Problems over Time-Varying Networks
Maxim Divilkovskiy, Alexander Gasnikov
We study non-smooth stochastic decentralized optimization problems over time-varying networks, where objective functions are distributed across nodes and network connections may in…
cs.CL2025
READER: Retrieval-Assisted Drafter for Efficient LLM Inference
Maxim Divilkovskiy, Vitaly Malygin, Sergey Zlobin +6
Autoregressive Language Models instantiate a factorized likelihood over token sequences, yet their strictly sequential decoding process imposes an intrinsic lower bound on inferenc…