← Back to all news
arXiv Machine Learning By Chang Qu, Zhaoyang Shi

BRACE: Differential Privacy for Dense Associative Memory with LSR Energy

Read the original on arXiv Machine Learning →

The paper introduces BRACE, a differentially private retrieval algorithm for log-sum-ReLU dense associative memory (LSR-DAM). BRACE adaptively corrects boundary-sensitive perturbations to control their cumulative effect during retrieval, achieving minimax optimal error rates that are independent of dimension and depend optimally on inverse temperature and retrieval horizon. The authors also prove central limit theorems for uncertainty quantification and demonstrate the method’s accuracy against baseline privacy approaches in numerical experiments.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Jul 23

Differentially Private Neural Network Training Under the Hidden State Assumption

arXiv:2407. 08233v3 Announce Type: replace Abstract: Current differentially private learning paradigms face a severe utility bottleneck: DP-SGD degrades performance through noise accumulation over training steps, while aggregation-based approaches such as PATE suffer from data inefficiency due to disjoint data partitioning.

By Ding Chen, Haochen Luo, Xiaofei Wang, Chen Liu
benchmarkssafety
More like this →
arXiv AI
Oct 12

DP-MIND: Differentially private memory-guided Long context Inference

DP-MIND is a memory‑guided framework that enables differentially private inference for large language models on million‑token contexts. It locally perturbs user queries and processes them in chunks, using a compact memory that retains task‑relevant information across the sequence. The memory construction is optimized via reinforcement learning on perturbed inputs, and a local denoising module recovers corrupted answer spans, resulting in improved scalability and utility over existing DP and long‑context inference baselines.

By Zhihao Liu, Yitian Cheng, Shuang Liu, Rui Wen, Yuke Hu, Zhan Qin
llmsreinforcement-learningbenchmarkssafety
More like this →
arXiv Machine Learning
Aug 12

Information Bottleneck under Perfect Privacy

arXiv:2608. 11003v1 Announce Type: cross Abstract: In this work, we study the information bottleneck under perfect privacy, with particular emphasis on the active-rate regime, where the representation-rate constraint is binding and directly limits the achievable utility.

By Junle Zhong, Mohamad Assaad, Sreejith Sreekumar
safety
More like this →