Search Results for author:
Found 24 papers, 10 papers with code
Beyond the Best: Estimating Distribution Functionals in Infinite-Armed Bandits
In the infinite-armed bandit problem, each arm's average reward is sampled from an unknown distribution, and each arm can be sampled further to obtain noisy estimates of the average reward of that arm.
Approximate Function Evaluation via Multi-Armed Bandits
We design an instance-adaptive algorithm that learns to sample according to the importance of each coordinate, and with probability at least $1-\delta$ returns an $\epsilon$ accurate estimate of $f(\boldsymbol{\mu})$.
Group-Structured Adversarial Training
Robust training methods against perturbations to the input data have received great attention in the machine learning literature.
Ebb-and-Flow Protocols: A Resolution of the Availability-Finality Dilemma
To resolve this availability-finality dilemma, we formulate a new class of flexible consensus protocols, ebb-and-flow protocols, which support a full dynamically available ledger in conjunction with a finalized prefix ledger.
Cryptography and Security Distributed, Parallel, and Cluster Computing
Ultra Fast Medoid Identification via Correlated Sequential Halving
Four to five orders of magnitude gains over exact computation are obtained on real data, in terms of both number of distance computations needed and wall clock time.
Boomerang: Redundancy Improves Latency and Throughput in Payment Networks
Funds are forwarded using Boomerang contracts, which allow Alice to revert the transfer iff she has learned Bob's secret.
Cryptography and Security Distributed, Parallel, and Cluster Computing Information Theory Networking and Internet Architecture Information Theory
Practical Low Latency Proof of Work Consensus
Bitcoin is the first fully-decentralized permissionless blockchain protocol to achieve a high level of security, but at the expense of poor throughput and latency.
Distributed, Parallel, and Cluster Computing Cryptography and Security Networking and Internet Architecture
Deconstructing Generative Adversarial Networks
Generalization: given a population target of GANs, we design a systematic principle, projection under admissible distance, to design GANs to meet the population requirement using finite samples.
Porcupine Neural Networks: Approximating Neural Network Landscapes
Neural networks have been used prominently in several machine learning and statistics applications.
Generalizable Adversarial Training via Spectral Normalization
A significant portion of this gap can be attributed to the decrease in generalization performance due to adversarial training.
A Convex Duality Framework for GANs
For a convex set $\mathcal{F}$, this duality framework interprets the original GAN formulation as finding the generative model with minimum JS-divergence to the distributions penalized to match the moments of the data distribution, with the moments specified by the discriminators in $\mathcal{F}$.
Hidden Hamiltonian Cycle Recovery via Linear Programming
Represented as bicolored multi-graphs, these extreme points are further decomposed into simpler "blossom-type" structures for the large deviation analysis and counting arguments.
A Spectral Approach to Generalization and Optimization in Neural Networks
The recent success of deep neural networks stems from their ability to generalize well on real data; however, Zhang et al. have observed that neural networks can easily overfit random labels.
Tensor Biclustering
Consider a dataset where data is collected on multiple features of multiple individuals over multiple times.
NeuralFDR: Learning Discovery Thresholds from Hypothesis Features
For example, in genetic association studies, each hypothesis tests the correlation between a variant and the trait.
Medoids in almost linear time via multi-armed bandits
Computing the medoid of a large number of points in high-dimensional space is an increasingly common operation in many data science problems.
Understanding GANs: the LQG Setting
Generative Adversarial Networks (GANs) have become a popular method to learn a probability model from data.
Porcupine Neural Networks: (Almost) All Local Optima are Global
Neural networks have been used prominently in several machine learning and statistics applications.
Time-Sensitive Bandit Learning and Satisficing Thompson Sampling
We propose satisficing Thompson sampling -- a variation of Thompson sampling -- and establish a strong discounted regret bound for this new algorithm.
Maximally Correlated Principal Component Analysis
For jointly Gaussian variables we show that the covariance matrix corresponding to the identity (or the negative of the identity) transformations majorizes covariance matrices of non-identity functions.
A Minimax Approach to Supervised Learning
Given a task of predicting $Y$ from $X$, a loss function $L$, and a set of probability distributions $\Gamma$ on $(X, Y)$, what is the optimal decision rule minimizing the worst-case expected loss over $\Gamma$?
Community Recovery in Graphs with Locality
Motivated by applications in domains such as social networks and computational biology, we study the problem of community recovery in graphs with locality.
Discrete Rényi Classifiers
We prove that for a given set of marginals, the minimum Hirschfeld-Gebelein-Renyi (HGR) correlation principle introduced in [1] leads to a randomized classification rule which is shown to have a misclassification rate no larger than twice the misclassification rate of the optimal classifier.
An Adaptive Successive Cancellation List Decoder for Polar Codes with Cyclic Redundancy Check
In this letter, we propose an adaptive SC (Successive Cancellation)-List decoder for polar codes with CRC.
Information Theory Information Theory
