18 citations · 21 across the 15 of their papers we have counts for
12 papers · 1 filter
From Approximation to Emergence: A Theory of Deep Learning
Zhilin Zhao
Deep learning has outgrown any single mathematical explanation. From Approximation to Emergence develops a unified, proof-oriented account of modern deep learning theory, tracing a…
Bridging Domain Expertise and Generalization for Performance Estimation
Shuxuan Li, Zhilin Zhao, Quyu Kong +1
Performance estimation under distribution shift aims to predict how a model behaves on an unlabeled test set whose distribution differs from the training data, a scenario that requ…
Federated Neural Nonparametric Point Processes
Hui Chen, Xuhui Fan, Hengyu Liu +5
Temporal point processes (TPPs) are effective for modeling event occurrences over time, but they struggle with sparse and uncertain events in federated systems, where privacy is a…
ParamReL: Learning Parameter Space Representation via Progressively Encoding Bayesian Flow Networks
Zhangkai Wu, Xuhui Fan, Jin Li +3
The recently proposed Bayesian Flow Networks~(BFNs) show great potential in modeling parameter spaces, offering a unified strategy for handling continuous, discretized, and discret…
Distilling the Unknown to Unveil Certainty
Zhilin Zhao, Longbing Cao, Yixuan Zhang +2
Out-of-distribution (OOD) detection is critical for identifying test samples that deviate from in-distribution (ID) data, ensuring network robustness and reliability. This paper pr…
R-divergence for Estimating Model-oriented Distribution Discrepancy
Zhilin Zhao, Longbing Cao
Real-life data are often non-IID due to complex distributions and interactions, and the sensitivity to the distribution of samples can differ among learning models. Accordingly, a…
Dual Representation Learning for Out-of-Distribution Detection
Zhilin Zhao, Longbing Cao
To classify in-distribution samples, deep neural networks explore strongly label-related information and discard weakly label-related information according to the information bottl…
Out-of-distribution Detection by Cross-class Vicinity Distribution of In-distribution Data
Zhilin Zhao, Longbing Cao, Kun-Yu Lin
Deep neural networks for image classification only learn to map in-distribution inputs to their corresponding ground truth labels in training without differentiating out-of-distrib…
Supervision Adaptation Balancing In-distribution Generalization and Out-of-distribution Detection
Zhilin Zhao, Longbing Cao, Kun-Yu Lin
The discrepancy between in-distribution (ID) and out-of-distribution (OOD) samples can lead to \textit{distributional vulnerability} in deep neural networks, which can subsequently…
Gray Learning from Non-IID Data with Out-of-distribution Samples
Zhilin Zhao, Longbing Cao, Chang-Dong Wang
The integrity of training data, even when annotated by experts, is far from guaranteed, especially for non-IID datasets comprising both in- and out-of-distribution samples. In an i…
Mixture of Online and Offline Experts for Non-stationary Time Series
Zhilin Zhao, Longbing Cao, Yuanyu Wan
We consider a general and realistic scenario involving non-stationary time series, consisting of several offline intervals with different distributions within a fixed offline time…
Revealing the Distributional Vulnerability of Discriminators by Implicit Generators
Zhilin Zhao, Longbing Cao, Kun-Yu Lin
In deep neural learning, a discriminator trained on in-distribution (ID) samples may make high-confidence predictions on out-of-distribution (OOD) samples. This triggers a signific…