6 papers
Black-Box Inference of LLM Architectural Properties with Restrictive API Access
Christopher Ellis, Shreyas Chaudhari, Mei-Yu Wang +3
In practice, most commercial LLM providers do not publicly release details of underlying LLM architectures. However, prior work has shown that given limited API access to an LLM (n…
GLUE: Gradient-free Learning to Unify Experts
Jong-Ik Park, Shreyas Chaudhari, Srinivasa Pranav +2
In many deployed systems (multilingual ASR, cross-hospital imaging, region-specific perception), multiple pretrained specialist models coexist. Yet, new target domains often requir…
GradNetOT: Learning Optimal Transport Maps with GradNets
Shreyas Chaudhari, Srinivasa Pranav, José M. F. Moura
Monotone gradient functions play a central role in solving the Monge formulation of the optimal transport (OT) problem, which arises in modern applications ranging from fluid dynam…
Peer-to-Peer Learning Dynamics of Wide Neural Networks
Shreyas Chaudhari, Srinivasa Pranav, Emile Anand +1
Peer-to-peer learning is an increasingly popular framework that enables beyond-5G distributed edge devices to collaboratively train deep neural networks in a privacy-preserving man…
ReLU Networks as Random Functions: Their Distribution in Probability Space
Shreyas Chaudhari, José M. F. Moura
This paper presents a novel framework for understanding trained ReLU networks as random, affine functions, where the randomness is induced by the distribution over the inputs. By c…
Gradient Networks
Shreyas Chaudhari, Srinivasa Pranav, José M. F. Moura
Directly parameterizing and learning gradients of functions has widespread significance, with specific applications in inverse problems, generative modeling, and optimal transport.…