6 papers
Calibrated -Barycenters for Multiobjective -Divergence Optimization
Dier Tang, Peijie Li, Xiaoyuan Zhang
Matching one distribution to many targets can require repeated evaluations of every target. CAL--MODM aggregates a nonlinear predictor into one barycenter, calibrates its residu…
Universal Distributed Feature Extraction Complementary to Side Information via H-Score
Yuan Xinjie, Dier Tang, Shaolun-Huang
This paper considers a distributed estimation system where edge nodes transmit averaged features to a center node for parameter estimation. A key challenge arises when the center n…
On the Cardinality of Optimal Representations in the Binary-Source Information Bottleneck
Dier Tang, Jun Chen
The information bottleneck (IB) seeks a representation of a source that retains as much information as possible about a target , subject to a constraint on . A c…
Mutual Information Constrained Chernoff Bottleneck
Dier Tang, Guangyue Han
The classical information bottleneck (IB) measures the relevance of a representation of to a target by , which does not directly characterize the error of downs…
Sharp Regret Bounds and a Task-Covariance Correction for Spectral Representation Learning
Dier Tang, Jing Yee Tan, Guangyue Han
Spectral features can remain optimal under strongly uneven task preferences when they retain the directions most useful to the tasks. In a local-task model, expected probing gain d…
Universal Feature Selection with Noisy Observations and Weak Symmetry Conditions
Dier Tang, Guangyue Han
This paper relaxes the restrictive symmetry conditions adopted in [4], [5] and extends their universal feature selection framework to accommodate noisy observations as well as attr…