1 citations · 1 across the 4 of their papers we have counts for
6 papers
Can Rényi Accountants Beat Lossless Accountants for DP-SGD?
Jinho Bok
Recent frameworks in differential privacy (DP), such as privacy loss distributions and -DP, provide lossless representations of the privacy leakage of mechanisms. These approach…
Detection of local geometry in random graphs: information-theoretic and computational limits
Jinho Bok, Shuangping Li, Sophie H. Yu
We study the problem of detecting local geometry in random graphs. We introduce a model , where a hidden community of average size has edges drawn as a…
Learning Acceleration Algorithms for Fast Parametric Convex Optimization with Certified Robustness
Rajiv Sambharya, Jinho Bok, Nikolai Matni +1
We develop a machine-learning framework to learn hyperparameter sequences for accelerated first-order methods (e.g., the step size and momentum sequences in accelerated gradient de…
Optimized methods for composite optimization: a reduction perspective
Jinho Bok, Jason M. Altschuler
Recent advances in convex optimization have leveraged computer-assisted proofs to develop optimized first-order methods that improve over classical algorithms. However, each optimi…
Accelerating Proximal Gradient Descent via Silver Stepsizes
Jinho Bok, Jason M. Altschuler
Surprisingly, recent work has shown that gradient descent can be accelerated without using momentum -- just by judiciously choosing stepsizes. An open question raised by several pa…
Shifted Interpolation for Differential Privacy
Jinho Bok, Weijie Su, Jason M. Altschuler
Noisy gradient descent and its variants are the predominant algorithms for differentially private machine learning. It is a fundamental question to quantify their privacy leakage,…