8 citations · 8 across the 9 of their papers we have counts for
5 papers · 1 filter
DiscQuant: A Quantization Method for Neural Networks Inspired by Discrepancy Theory
Jerry Chee, Arturs Backurs, Rainie Heck +4
Quantizing the weights of a neural network has two steps: (1) Finding a good low bit-complexity representation for weights (which we call the quantization grid) and (2) Rounding th…
Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generation
Xinyu Tang, Richard Shin, Huseyin A. Inan +6
We study the problem of in-context learning (ICL) with large language models (LLMs) on private datasets. This scenario poses privacy risks, as LLMs may leak or regurgitate the priv…
Selective Pre-training for Private Fine-tuning
Da Yu, Sivakanth Gopi, Janardhan Kulkarni +5
Text prediction models, when used in applications like email clients or word processors, must protect user data privacy and adhere to model size constraints. These constraints are…
Differentially Private n-gram Extraction
Kunho Kim, Sivakanth Gopi, Janardhan Kulkarni +1
We revisit the problem of -gram extraction in the differential privacy setting. In this problem, given a corpus of private text data, the goal is to release as many -grams as…
Fast and Memory Efficient Differentially Private-SGD via JL Projections
Zhiqi Bu, Sivakanth Gopi, Janardhan Kulkarni +3
Differentially Private-SGD (DP-SGD) of Abadi et al. (2016) and its variations are the only known algorithms for private training of large scale neural networks. This algorithm requ…