Asia
Symbol-LLM: Leverage Language Models for Symbolic System in Visual Human Activity Reasoning
Human reasoning can be understood as a cooperation between the intuitive, associative "System-1" and the deliberative, logical "System-2".
Confidence-based Reliable Learningunder Dual Noises
Filteringx-noiseusing W noise. Inspired weutilizex-noise.
A Universal Growth Rate for Learning with Smooth Surrogate Losses
We first examine how H -consistency bounds vary across surrogates based on the number of classes.
Uncertainty-Aware Attention for Reliable Interpretation and Prediction
Jay Heo, Hae Beom Lee, Saehoon Kim, Juho Lee, Kwang Joon Kim, Eunho Yang, Sung Ju Hwang
Neural Information Processing Systems http://nips.cc/
Differentially Private Algorithms for Learning Mixtures of Separated Gaussians
Gautam Kamath, Or Sheffet, Vikrant Singhal, Jonathan Ullman
In this work, westudy algorithms for learning Gaussian mixtures subject todifferential privacy[32], which has become thede facto standard for individual privacy in statistical analysis of sensitive data. Intuitively, differential privacy guarantees that the output of the algorithm does not depend significantly on any one individual's data, which in this case means any one sample.
280cf18baf4311c92aa5a042336587d3-Paper.pdf
A recent line of work has uncovered a new form of data poisoning: so-called backdoorattacks. These attacks are particularly dangerous because they do not affect a network's behavior on typical, benign data.
Structured Variational Inference in Continuous Cox Process Models
Virginia Aglietti, Edwin V. Bonilla, Theodoros Damoulas, Sally Cripps
This view enables a structured variational approximation capturing dependencies across variables in the model.