activity
20162026
most citedDifferentially Private Fine-tuning of Language Models

47 citations · 214 across the 48 of their papers we have counts for

collaborators
Showing 2021Show all

9 papers · 1 filter

cs.LG2021

Optimizing Information-theoretical Generalization Bounds via Anisotropic Noise in SGLD

Bohan Wang, Huishuai Zhang, Jieyu Zhang +3

Recently, the information-theoretical framework has been proven to be able to obtain non-vacuous generalization bounds for large models trained by Stochastic Gradient Langevin Dyna…

cs.LG2021★ 33 cited

Availability Attacks Create Shortcuts

Da Yu, Huishuai Zhang, Wei Chen +2

Availability attacks, which poison the training data with imperceptible perturbations, can make the data \emph{not exploitable} by machine learning algorithms so as to prevent unau…

cs.LG2021★ 47 cited

Differentially Private Fine-tuning of Language Models

Da Yu, Saurabh Naik, Arturs Backurs +9

We give simpler, sparser, and faster algorithms for differentially private fine-tuning of large-scale pre-trained language models, which achieve the state-of-the-art privacy versus…

cs.LG2021

Does Momentum Change the Implicit Regularization on Separable Data?

Bohan Wang, Qi Meng, Huishuai Zhang +4

The momentum acceleration technique is widely adopted in many optimization algorithms. However, there is no theoretical answer on how the momentum affects the generalization perfor…

cs.LG2021

Regularized OFU: an Efficient UCB Estimator forNon-linear Contextual Bandit

Yichi Zhou, Shihong Song, Huishuai Zhang +3

Balancing exploration and exploitation (EE) is a fundamental problem in contex-tual bandit. One powerful principle for EE trade-off isOptimism in Face of Uncer-tainty(OFU), in whic…

cs.LG2021★ 14 cited

Large Scale Private Learning via Low-rank Reparametrization

Da Yu, Huishuai Zhang, Wei Chen +2

We propose a reparametrization scheme to address the challenges of applying differentially private SGD on large neural networks, which are 1) the huge memory cost of storing indivi…