Search Results for author:
Found 14 papers, 0 papers with code
Secure Aggregation is Not Private Against Membership Inference Attacks
In this paper, we delve into the privacy implications of SecAgg by treating it as a local differential privacy (LDP) mechanism for each local update.
A TDD Distributed MIMO Testbed Using a 1-Bit Radio-Over-Fiber Fronthaul Architecture
The CU is connected to multiple single-antenna remote radio heads (RRHs) via optical fibers, over which a binary RF waveform is transmitted.
Generalization Bounds: Perspectives from Information Theory and PAC-Bayes
Over the past decades, the PAC-Bayesian approach has been established as a flexible framework to address the generalization capabilities of machine learning algorithms, and design new ones.
A New Family of Generalization Bounds Using Samplewise Evaluated CMI
Furthermore, using the evaluated CMI, we derive a samplewise, average version of Seeger's PAC-Bayesian bound, where the convex function is the binary KL divergence.
Evaluated CMI Bounds for Meta Learning: Tightness and Expressiveness
Recent work has established that the conditional mutual information (CMI) framework of Steinke and Zakynthinou (2020) is expressive enough to capture generalization guarantees in terms of algorithmic stability, VC dimension, and related complexity measures for conventional learning (Harutyunyan et al., 2021, Haghifam et al., 2021).
Resolution-Adaptive All-Digital Spatial Equalization for mmWave Massive MU-MIMO
All-digital basestation (BS) architectures for millimeter-wave (mmWave) massive multi-user multiple-input multiple-output (MU-MIMO), which equip each radio-frequency chain with dedicated data converters, have advantages in spectral efficiency, flexibility, and baseband-processing simplicity over hybrid analog-digital solutions.
Distortion-Aware Linear Precoding for Massive MIMO Downlink Systems with Nonlinear Power Amplifiers
By studying the spatial characteristics of the distortion, we demonstrate that conventional linear precoding techniques steer nonlinear distortions towards the users.
Information Theory Signal Processing Information Theory
Transfer Meta-Learning: Information-Theoretic Bounds and Information Meta-Risk Minimization
In this paper, we introduce the problem of transfer meta-learning, in which tasks are drawn from a target task environment during meta-testing that may differ from the source task environment observed during meta-training.
Fast-Rate Loss Bounds via Conditional Information Measures with Applications to Neural Networks
If the conditional information density is bounded uniformly in the size $n$ of the training set, our bounds decay as $1/n$.
Conditional Mutual Information-Based Generalization Bound for Meta Learning
Meta-learning optimizes an inductive bias---typically in the form of the hyperparameters of a base-learning algorithm---by observing data from a finite number of related tasks.
Nonvacuous Loss Bounds with Fast Rates for Neural Networks via Conditional Information Measures
If the conditional information density is bounded uniformly in the size $n$ of the training set, our bounds decay as $1/n$, which is referred to as a fast rate.
High-Bandwidth Spatial Equalization for mmWave Massive MU-MIMO with Processing-In-Memory
All-digital basestation (BS) architectures enable superior spectral efficiency compared to hybrid solutions in massive multi-user MIMO systems.
Generalization Bounds via Information Density and Conditional Information Density
We present a general approach, based on exponential inequalities, to derive bounds on the generalization error of randomized learning algorithms.
Generalization Error Bounds via $m$th Central Moments of the Information Density
Our approach can be used to obtain bounds on the average generalization error as well as bounds on its tail probabilities, both for the case in which a new hypothesis is randomly generated every time the algorithm is used - as often assumed in the probably approximately correct (PAC)-Bayesian literature - and in the single-draw case, where the hypothesis is extracted only once.
