2 citations · 2 across the 7 of their papers we have counts for
9 papers
A Two-Dimensional Extremizer for Relatively Inexact Gradient Descent
Jinze Zhao
We give an explicit extremal function for one step of gradient descent when the gradient error is bounded relative to the true gradient. The function is the sum of a quadratic in o…
Sharpness and Rigidity of the Two-Factor Recht-Re Lower Bound
Jinze Zhao
Products of positive semidefinite matrices arise when successive steps of a randomized optimization method use different data points. Their average can have a negative eigenvalue e…
Small-Ball Marginals Do Not Control Restricted Eigenvalues by Euclidean Gaussian Width
Jinze Zhao
Banerjee, Chen, and Sivakumar asked at COLT 2015 whether a uniform small-ball condition on the rows of a random design matrix forces a restricted-eigenvalue lower bound whose sampl…
Predicting Diagonalizability of a Mean Matrix
Jinze Zhao
Wu and Santhanam asked whether one can determine, from an increasing i.i.d. sample of binary random matrices, whether the unknown mean matrix is diagonalizable while making only fi…
From Approachability Residuals to Anytime-Valid Evidence: The Online Convex Geometry of Testing by Betting
Jinze Zhao
Betting-based sequential tests and Blackwell approachability are linked by a rate-explicit reduction through support-function residuals. For a compact convex target and vector…
Sparse Mixture-of-Experts for Compositional Generalization: Empirical Evidence and Theoretical Foundations of Optimal Sparsity
Jinze Zhao, Peihao Wang, Junjie Yang +6
Sparse Mixture-of-Experts (SMoE) architectures have gained prominence for their ability to scale neural networks, particularly transformers, without a proportional increase in comp…
Generalization Error Analysis for Sparse Mixture-of-Experts: A Preliminary Study
Jinze Zhao, Peihao Wang, Zhangyang Wang
Mixture-of-Experts (MoE) represents an ensemble methodology that amalgamates predictions from several specialized sub-models (referred to as experts). This fusion is accomplished t…
Meta ControlNet: Enhancing Task Adaptation via Meta Learning
Junjie Yang, Jinze Zhao, Peihao Wang +2
Diffusion-based image synthesis has attracted extensive attention recently. In particular, ControlNet that uses image-based prompts exhibits powerful capability in image tasks such…
CrossEAI: Using Explainable AI to generate better bounding boxes for Chest X-ray images
Jinze Zhao
Explainability is critical for deep learning applications in healthcare which are mandated to provide interpretations to both patients and doctors according to legal regulations an…