Search Results for author:
Found 8 papers, 2 papers with code
Robust Score-Based Quickest Change Detection
This work considers the case where the pre- and post-change score functions are known only to correspond to distributions in two disjoint sets.
ColA: Collaborative Adaptation with Gradient Learning
We introduce Collaborative Adaptation (ColA) with Gradient Learning (GL), a parameter-free, model-agnostic fine-tuning approach that decouples the computation of the gradient of hidden representations and parameters.
Quickest Change Detection for Unnormalized Statistical Models
This paper develops a new variant of the classical Cumulative Sum (CUSUM) algorithm for the quickest change detection.
Minimax Concave Penalty Regularized Adaptive System Identification
We develop a recursive least square (RLS) type algorithm with a minimax concave penalty (MCP) for adaptive identification of a sparse tap-weight vector that represents a communication channel.
On The Energy Statistics of Feature Maps in Pruning of Neural Networks with Skip-Connections
We propose a new structured pruning framework for compressing Deep Neural Networks (DNNs) with skip connections, based on measuring the statistical dependency of hidden layers and predicted outputs.
Multi-Agent Adversarial Attacks for Multi-Channel Communications
In particular, by modeling the adversaries as learning agents, we show that the proposed MAAS is able to successfully choose the transmitted channel(s) and their respective allocated power(s) without any prior knowledge of the sender strategy.
Model-Free Energy Distance for Pruning DNNs
We measure a new model-free information between the feature maps and the output of the network.
Deep Clustering of Compressed Variational Embeddings
Motivated by the ever-increasing demands for limited communication bandwidth and low-power consumption, we propose a new methodology, named joint Variational Autoencoders with Bernoulli mixture models (VAB), for performing clustering in the compressed data domain.
