Search Results for author:
Found 7 papers, 2 papers with code
Diversity Based Edge Pruning of Neural Networks Using Determinantal Point Processes
We then empirically show that DPP edge pruning for neural networks outperforms other competing methods (both edge and node) on real data.
Understanding Diversity Based Neural Network Pruning in Teacher Student Setup
Despite multitude of empirical advances, there is a lack of theoretical understanding of the effectiveness of different pruning methods.
Fairness in Rating Prediction by Awareness of Verbal and Gesture Quality of Public Speeches
Our work ties together a novel metric for public speeches in both verbal and non-verbal domain with the computational power of a neural network to design a fair prediction system for speakers.
Statistical Mechanical Analysis of Neural Network Pruning
We inspect different pruning techniques under the statistical mechanics formulation of a teacher-student framework and derive their generalization error (GE) bounds.
Detection and Mitigation of Bias in Ted Talk Ratings
Unbiased data collection is essential to guaranteeing fairness in artificial intelligence models.
FairyTED: A Fair Rating Predictor for TED Talk Data
This causal model contributes in generating counterfactual data to train a fair predictive model.
Weighted Theta Functions and Embeddings with Applications to Max-Cut, Clustering and Summarization
We introduce a unifying generalization of the Lovász theta function, and the associated geometric embedding, for graphs with weights on both nodes and edges.
