6 papers
Fundamental limits of distributed multiclass classification from simple binary decisions
Ioannis Papageorgiou, Srinivas Nomula, Ayalvadi Ganesh +2
We consider the problem of constructing a -class classifier from the combination of simple binary classifiers -- this is a natural paradigm to construct a sophistica…
Self-Creating Random Walks for Decentralized Learning under Pac-Man Attacks
Xingran Chen, Parimal Parag, Rohit Bhagat +1
Random walk (RW)-based algorithms have long been popular in distributed systems due to low overheads and scalability, with recent growing applications in decentralized learning. Ho…
Random Walk Learning and the Pac-Man Attack
Xingran Chen, Parimal Parag, Rohit Bhagat +2
Random walk (RW)-based algorithms have long been popular in distributed systems due to low overheads and scalability, with recent growing applications in decentralized learning. Ho…
Perfect Privacy and Strong Stationary Times for Markovian Sources
Fangwei Ye, Zonghong Liu, Parimal Parag +1
We consider the problem of sharing correlated data under a perfect information-theoretic privacy constraint. We focus on redaction (erasure) mechanisms, in which data are either wi…
Bipartite matching under communication constraints
Moonmoon Mohanty, Gautham Bolar, Preetam Patil +3
In modern data center networks, thousands of hosts contend for shared link capacity; the scale of these systems makes centralized scheduling impractical. This article models such s…
Optimizing Resource Allocation for Geographically-Distributed Inference by Large Language Models
Tingyang Sun, Ting He, Bo Ji +1
Large language models have demonstrated extraordinary performance in many AI tasks but are expensive to use, even after training, due to their requirement of high-end GPUs. Recentl…