Search Results for author:
Found 24 papers, 2 papers with code
Learning Mixtures of Separable Dictionaries for Tensor Data: Analysis and Algorithms
This work addresses the problem of learning sparse representations of tensor data using structured dictionary learning.
Distributed Differentially Private Computation of Functions with Correlated Noise
CAPE can be used in conjunction with the functional mechanism for statistical and machine learning optimization problems.
Identifiability of Kronecker-structured Dictionaries for Tensor Data
This paper derives sufficient conditions for local recovery of coordinate dictionaries comprising a Kronecker-structured dictionary that is used for representing $K$th-order tensor data.
Distributed Differentially-Private Algorithms for Matrix and Tensor Factorization
Tensor and matrix factorizations are key components of many processing pipelines.
STARK: Structured Dictionary Learning Through Rank-one Tensor Recovery
In recent years, a class of dictionaries have been proposed for multidimensional (tensor) data representation that exploit the structure of tensor data by imposing a Kronecker structure on the dictionary underlying the data.
High Dimensional Inference with Random Maximum A-Posteriori Perturbations
This paper shows that the expected value of perturb-max inference with low dimensional perturbations can be used sequentially to generate unbiased samples from the Gibbs distribution.
Minimax Lower Bounds for Kronecker-Structured Dictionary Learning
This paper finds fundamental limits on the sample complexity of estimating dictionaries for tensor data by proving a lower bound on the minimax risk.
Auditing: Active Learning with Outcome-Dependent Query Costs
We term the setting auditing, and consider the auditing complexity of an algorithm: the number of negative labels the algorithm requires in order to learn a hypothesis with low relative error.
Learning from Data with Heterogeneous Noise using SGD
In this paper, we adopt instead a model in which data is observed through heterogeneous noise, where the noise level reflects the quality of the data source.
On Measure Concentration of Random Maximum A-Posteriori Perturbations
Applying the general result to MAP perturbations can yield a more efficient algorithm to approximate sampling from the Gibbs distribution.
Near-Optimal Algorithms for Differentially-Private Principal Components
In this paper we investigate the theory and empirical performance of differentially private approximations to PCA and propose a new method which explicitly optimizes the utility of the output.
Predictive Learning on Hidden Tree-Structured Ising Models
In the absence of noise, predictive learning on Ising models was recently studied by Bresler and Karzand (2020); this paper quantifies how noise in the hidden model impacts the tasks of structure recovery and marginal distribution estimation by proving upper and lower bounds on the sample complexity.
Optimal Rates for Learning Hidden Tree Structures
Specifically, we show that the finite sample complexity of the Chow-Liu algorithm for ensuring exact structure recovery from noisy data is inversely proportional to the information threshold squared (provided it is positive), and scales almost logarithmically relative to the number of nodes over a given probability of failure.
Improved Differentially Private Decentralized Source Separation for fMRI Data
In this work, we propose a differentially private algorithm for performing ICA in a decentralized data setting.
Quantile Multi-Armed Bandits: Optimal Best-Arm Identification and a Differentially Private Scheme
First, we propose a (non-private) successive elimination algorithm for strictly optimal best-arm identification, we show that our algorithm is $\delta$-PAC and we characterize its sample complexity.
Influencers and the Giant Component: the Fundamental Hardness in Privacy Protection for Socially Contagious Attributes
Experiments demonstrate that a giant connected component of infected nodes can and does appear in real-world networks and that a simple inference attack can reveal the status of a good fraction of nodes.
Inference Attack
Social and Information Networks
A Minimax Lower Bound for Low-Rank Matrix-Variate Logistic Regression
This paper considers the problem of matrix-variate logistic regression.
Network Traffic Shaping for Enhancing Privacy in IoT Systems
We show that in special cases the proposed mechanism recovers existing shapers which standardize the output independently from the input.
Low-Rank Phase Retrieval with Structured Tensor Models
We study the low-rank phase retrieval problem, where the objective is to recover a sequence of signals (typically images) given the magnitude of linear measurements of those signals.
TorchNTK: A Library for Calculation of Neural Tangent Kernels of PyTorch Models
We introduce torchNTK, a python library to calculate the empirical neural tangent kernel (NTK) of neural network models in the PyTorch framework.
Privacy Leakage in Discrete Time Updating Systems
We analyze the trade-off between the age of information (AoI) and the maximal leakage for systems in which the source generates updates as a Bernoulli process.
Minibatching Offers Improved Generalization Performance for Second Order Optimizers
Training deep neural networks (DNNs) used in modern machine learning is computationally expensive.
Structured Low-Rank Tensors for Generalized Linear Models
This result can also be specialised to lower bound the estimation error in CP and Tucker-structured GLMs.
Robust Nonparametric Hypothesis Testing to Understand Variability in Training Neural Networks
Training a deep neural network (DNN) often involves stochastic optimization, which means each run will produce a different model.
