1 citations · 1 across the 5 of their papers we have counts for
5 papers
The Disparate Impacts of Speculative Decoding
Jameson Sandler, Ahmet Üstün, Marco Romanelli +2
The practice of speculative decoding, whereby inference is probabilistically supported by a smaller, cheaper, ``drafter'' model, has become a standard technique for systematically…
Low-rank finetuning for LLMs: A fairness perspective
Saswat Das, Marco Romanelli, Cuong Tran +3
Low-rank approximation techniques have become the de facto standard for fine-tuning Large Language Models (LLMs) due to their reduced computational and memory requirements. This pa…
On the (In)feasibility of ML Backdoor Detection as an Hypothesis Testing Problem
Georg Pichler, Marco Romanelli, Divya Prakash Manivannan +3
We introduce a formal statistical definition for the problem of backdoor detection in machine learning systems and use it to analyze the feasibility of such problems, providing evi…
Disparate Impact on Group Accuracy of Linearization for Private Inference
Saswat Das, Marco Romanelli, Ferdinando Fioretto
Ensuring privacy-preserving inference on cryptographically secure data is a well-known computational challenge. To alleviate the bottleneck of costly cryptographic computations in…
Retrieval-Guided Reinforcement Learning for Boolean Circuit Minimization
Animesh Basak Chowdhury, Marco Romanelli, Benjamin Tan +2
Logic synthesis, a pivotal stage in chip design, entails optimizing chip specifications encoded in hardware description languages like Verilog into highly efficient implementations…