![Loading...](https://link.springer.com/static/c4a417b97a76cc2980e3c25e2271af3129e08bbe/images/pdf-preview/spacer.gif)
-
Article
An accelerated proximal algorithm for regularized nonconvex and nonsmooth bi-level optimization
Many important machine learning applications involve regularized nonconvex bi-level optimization. However, the existing gradient-based bi-level optimization algorithms cannot handle nonconvex or nonsmooth regu...
-
Article
Open AccessExplainable machine learning in materials science
Machine learning models are increasingly used in materials studies because of their exceptional accuracy. However, the most accurate machine learning models are usually difficult to explain. Remedies to this p...
-
Chapter and Conference Paper
A Spectral View of Randomized Smoothing Under Common Corruptions: Benchmarking and Improving Certified Robustness
Certified robustness guarantee gauges a model’s resistance to test-time attacks and can assess the model’s readiness for deployment in the real world. In this work, we explore a new problem setting to critical...
-
Article
MimicGAN: Robust Projection onto Image Manifolds with Corruption Mimicking
In the past few years, Generative Adversarial Networks (GANs) have dramatically advanced our ability to represent and parameterize high-dimensional, non-linear image manifolds. As a result, they have been wide...
-
Article
Open AccessReliable and explainable machine-learning methods for accelerated material discovery
Despite ML’s impressive performance in commercial applications, several unique challenges exist when applying ML in materials science applications. In such a context, the contributions of this work are twofold...
-
Chapter
Background
This chapter introduces the mathematical background of conventional inference by describing the typical inference problems of detection, estimation, classification, and tracking. Specific challenges associated...
-
Chapter
Introduction
We are living in an increasingly networked world with sensing networks that are often comprised of numerous sensing devices (or agents) of varying sizes, communicating with each other via different topologies....
-
Chapter
Some Additional Topics on Distributed Inference
While the previous two chapters considered the problems of distributed detection and estimation in the presence of Byzantines and with binary quantized data, this chapter focuses on their generalizations. Spec...
-
Chapter
Distributed Estimation and Target Localization
In this chapter, distributed parameter estimation problems are discussed with special emphasis on target localization in WSNs. Following the structure outlined in Chap. 2
-
Chapter
Distributed Inference with Unreliable Data: Some Unconventional Directions
In this chapter, some recent directions in networked inference with Byzantines are discussed. More specifically, the concept of Friendly Byzantines is presented where cooperative Byzantines are intentionally intr...
-
Chapter
Distributed Detection with Unreliable Data Sources
In this chapter, we discuss networked detection problems for several practical network architectures such as parallel, multi-hop, and fully autonomous ad hoc networks. Following the taxonomy presented earlier,...