Search Results for author:
Found 17 papers, 5 papers with code
Understanding Self-Distillation and Partial Label Learning in Multi-Class Classification with Label Noise
By deriving a closed-form solution for the student model's outputs, we discover that SD essentially functions as label averaging among instances with high feature correlations.
Efficient Algorithms for Exact Graph Matching on Correlated Stochastic Block Models with Constant Correlation
We consider the problem of graph matching, or learning vertex correspondence, between two correlated stochastic block models (SBMs).
Detection problems in the spiked matrix models
We first show that the principal component analysis can be improved by entrywise pre-transforming the data matrix if the noise is non-Gaussian, generalizing the known results for the spiked random matrix models with rank-1 signals.
Data Valuation Without Training of a Model
Many recent works on understanding deep learning try to quantify how much individual data instances influence the optimization and generalization of a model.
Recovering Top-Two Answers and Confusion Probability in Multi-Choice Crowdsourcing
Under this model, we propose a two-stage inference algorithm to infer both the top two answers and the confusion probability.
Test-Time Adaptation via Self-Training with Nearest Neighbor Information
To overcome this limitation, we propose a novel test-time adaptation method, called Test-time Adaptation via Self-Training with nearest neighbor information (TAST), which is composed of the following procedures: (1) adds trainable adaptation modules on top of the trained feature extractor; (2) newly defines a pseudo-label distribution for the test data by using the nearest neighbor information; (3) trains these modules only a few times during test time to match the nearest neighbor-based pseudo label distribution and a prototype-based class distribution for the test data; and (4) predicts the label of test data using the average predicted class distribution from these modules.
Asymptotic Normality of Log Likelihood Ratio and Fundamental Limit of the Weak Detection for Spiked Wigner Matrices
For general non-Gaussian noise, assuming that the signal is drawn from the Rademacher prior, we prove that the log likelihood ratio (LR) of the spiked model against the null model converges to a Gaussian when the signal-to-noise ratio is below a certain threshold.
A Worker-Task Specialization Model for Crowdsourcing: Efficient Inference and Fundamental Limits
Inferring correct labels from multiple noisy answers on data, however, has been a challenging problem, since the quality of the answers varies widely across tasks and workers.
Detection of Signal in the Spiked Rectangular Models
We show that the principal component analysis can be improved by pre-transforming the matrix entries if the noise is non-Gaussian.
Self-Diagnosing GAN: Diagnosing Underrepresented Samples in Generative Adversarial Networks
To promote diversity in sample generation without degrading the overall quality, we propose a simple yet effective method to diagnose and emphasize underrepresented samples during training of a GAN.
Robust Hypergraph Clustering via Convex Relaxation of Truncated MLE
We study hypergraph clustering in the weighted $d$-uniform hypergraph stochastic block model ($d$\textsf{-WHSBM}), where each edge consisting of $d$ nodes from the same community has higher expected weight than the edges consisting of nodes from different communities.
Crowdsourced Labeling for Worker-Task Specialization Model
We consider crowdsourced labeling under a $d$-type worker-task specialization model, where each worker and task is associated with one particular type among a finite set of types and a worker provides a more reliable answer to tasks of the matched type than to tasks of unmatched types.
Binary Classification with XOR Queries: Fundamental Limits and An Efficient Algorithm
In particular, we consider the problem of classifying $m$ binary labels with XOR queries that ask whether the number of objects having a given attribute in the chosen subset of size $d$ is even or odd.
Weak Detection in the Spiked Wigner Model with General Rank
We study the statistical decision process of detecting the signal from a `signal+noise' type matrix model with an additive Wigner noise.
Shallow Neural Network can Perfectly Classify an Object following Separable Probability Distribution
This paper constructs shallow sigmoid-type neural networks that achieve 100% accuracy in classification for datasets following a linear separability condition.
Weak detection in the spiked Wigner model
We propose a hypothesis test on the presence of the signal by utilizing the linear spectral statistics of the data matrix.
Parity Queries for Binary Classification
We define the query difficulty $\bar{d}$ as the average size of the query subsets and the sample complexity $n$ as the minimum number of measurements required to attain a given recovery accuracy.
