Search Results for author:
Found 56 papers, 6 papers with code
Scalable K-Means++
The recently proposed k-means++ initialization algorithm achieves this, obtaining an initial set of centers that is provably close to the optimum solution.
Databases
Selecting Diverse Features via Spectral Regularization
We compare our algorithms to traditional greedy and $\ell_1$-regularization schemes and show that we obtain a more diverse set of features that result in the regression problem being stable under perturbations.
Conversational flow in Oxford-style debates
Public debates are a common platform for presenting and juxtaposing diverging views on important issues.
On Mixtures of Markov Chains
We study the problem of reconstructing a mixture of Markov chains from the trajectories generated by random walks through the state space.
Algorithms for $\ell_p$ Low-Rank Approximation
We consider the problem of approximating a given matrix by a low-rank matrix so as to minimize the entrywise $\ell_p$-approximation error, for any $p \geq 1$; the case $p = 2$ is the classical SVD problem.
Fair Clustering Through Fairlets
We show that any fair clustering problem can be decomposed into first finding good fairlets, and then using existing machinery for traditional clustering algorithms.
Learning a Mixture of Two Multinomial Logits
In this model, a user is offered a slate of choices (a subset of a finite universe of $n$ items), and selects exactly one item from the slate, each with probability proportional to its (positive) weight.
Improving Online Algorithms via ML Predictions
In this work we study the problem of using machine-learned predictions to improve performance of online algorithms.
Mallows Models for Top-k Lists
The classic Mallows model is a widely-used tool to realize distributions on per- mutations.
On the Learnability of Deep Random Networks
In this paper we study the learnability of deep random networks from both theoretical and practical points of view.
Clustering without Over-Representation
In this paper we consider clustering problems in which each point is endowed with a color.
Testing Mixtures of Discrete Distributions
In our model, the noisy distribution is a mixture of the original distribution and noise, where the latter is known to the tester either explicitly or via sample access; the form of the noise is also known a priori.
On the Power of Multiple Anonymous Messages
- Protocols in the multi-message shuffled model with $poly(\log{B}, \log{n})$ bits of communication per user and $poly\log{B}$ error, which provide an exponential improvement on the error compared to what is possible with single-message algorithms.
Preventing Adversarial Use of Datasets through Fair Core-Set Construction
We propose improving the privacy properties of a dataset by publishing only a strategically chosen "core-set" of the data containing a subset of the instances.
Efficient Rematerialization for Deep Networks
When training complex neural networks, memory usage can be an important bottleneck.
Fair Correlation Clustering
We define a fairlet decomposition with cost similar to the $k$-median cost and this allows us to obtain approximation algorithms for a wide range of fairness constraints.
Online Learning with Imperfect Hints
We consider a variant of the classical online linear optimization problem in which at every step, the online player receives a "hint" vector before choosing the action for that round.
A Note on Double Pooling Tests
We present double pooling, a simple, easy-to-implement variation on test pooling, that in certain ranges for the a priori probability of a positive test, is significantly more efficient than the standard single pooling approach (the Dorfman method).
Discrete Mathematics Information Theory Information Theory Methodology
Fair Hierarchical Clustering
As machine learning has become more prevalent, researchers have begun to recognize the necessity of ensuring machine learning systems are fair.
Near-tight closure bounds for Littlestone and threshold dimensions
We study closure properties for the Littlestone and threshold dimensions of binary hypothesis classes.
Differentially Private Clustering: Tight Approximation Ratios
For several basic clustering problems, including Euclidean DensestBall, 1-Cluster, k-means, and k-median, we give efficient differentially private algorithms that achieve essentially the same approximation ratios as those that can be obtained by any non-private algorithm, while incurring only small additive errors.
On Distributed Differential Privacy and Counting Distinct Elements
We study the setup where each of $n$ users holds an element from a discrete set, and the goal is to count the number of distinct elements across all users, under the constraint of $(\epsilon, \delta)$-differentially privacy: - In the non-interactive local setting, we prove that the additive error of any protocol is $\Omega(n)$ for any constant $\epsilon$ and for any $\delta$ inverse polynomial in $n$.
Online Linear Optimization with Many Hints
We study an online linear optimization (OLO) problem in which the learner is provided access to $K$ "hint" vectors in each round prior to making a decision.
On Additive Approximate Submodularity
We show that an approximately submodular function defined on a ground set of $n$ elements is $O(n^2)$ pointwise-close to a submodular function.
Robust and Private Learning of Halfspaces
In this work, we study the trade-off between differential privacy and adversarial robustness under L2-perturbations in the context of learning halfspaces.
Sample-efficient proper PAC learning with approximate differential privacy
In this paper we prove that the sample complexity of properly learning a class of Littlestone dimension $d$ with approximate differential privacy is $\tilde O(d^6)$, ignoring privacy and accuracy parameters.
On Avoiding the Union Bound When Answering Multiple Differentially Private Queries
On the other hand, the algorithm of Dagan and Kur has a remarkable advantage that the $\ell_{\infty}$ error bound of $O(\frac{1}{\epsilon}\sqrt{k \log \frac{1}{\delta}})$ holds not only in expectation but always (i. e., with probability one) while we can only get a high probability (or expected) guarantee on the error.
Deep Learning with Label Differential Privacy
The Randomized Response (RR) algorithm is a classical technique to improve robustness in survey aggregation, and has been widely adopted in applications with differential privacy guarantees.
Performance Dependency of LSTM and NAR Beamformers With Respect to Sensor Array Properties in V2I Scenario
In this work , Long short term based (LSTM) based deep learning and non linear auto regresive technique based regressor have been employed to predict the angles between the road side units and user equipment . Advance prediction of transmit and receive signals enables reliable vehicle to infrastructure communication.
Locally Private k-Means in One Round
We provide an approximation algorithm for k-means clustering in the one-round (aka non-interactive) local model of differential privacy (DP).
Large-Scale Differentially Private BERT
In this work, we study the large-scale pretraining of BERT-Large with differentially private SGD (DP-SGD).
User-Level Private Learning via Correlated Sampling
Most works in learning with differential privacy (DP) have focused on the setting where each user has a single sample.
Logarithmic Regret from Sublinear Hints
We consider the online linear optimization problem, where at every step the algorithm plays a point $x_t$ in the unit ball, and suffers loss $\langle c_t, x_t\rangle$ for some cost vector $c_t$ that is then revealed to the algorithm.
Online Knapsack with Frequency Predictions
There has been recent interest in using machine-learned predictions to improve the worst-case guarantees of online algorithms.
User-Level Differentially Private Learning via Correlated Sampling
Most works in learning with differential privacy (DP) have focused on the setting where each user has a single sample.
Parsimonious Learning-Augmented Caching
Learning-augmented algorithms -- in which, traditional algorithms are augmented with machine-learned predictions -- have emerged as a framework to go beyond worst-case analysis.
Machine Learning based Framework for Robust Price-Sensitivity Estimation with Application to Airline Pricing
To address this concern, we propose a two-stage estimation methodology which makes the estimation of the price-sensitivity parameters robust to biases in the estimators of the nuisance parameters of the model.
Faster Privacy Accounting via Evolving Discretization
We introduce a new algorithm for numerical composition of privacy random variables, useful for computing the accurate differential privacy parameters for composition of mechanisms.
Connect the Dots: Tighter Discrete Approximations of Privacy Loss Distributions
The privacy loss distribution (PLD) provides a tight characterization of the privacy loss of a mechanism in the context of differential privacy (DP).
Enhancement to Training of Bidirectional GAN : An Approach to Demystify Tax Fraud
To validate the proposed approach, we train a BiGAN with the proposed training approach to detect taxpayers, who are manipulating their tax returns.
Algorithms with More Granular Differential Privacy Guarantees
Differential privacy is often applied with a privacy parameter that is larger than the theory suggests is ideal; various informal justifications for tolerating large privacy parameters have been proposed.
Anonymized Histograms in Intermediate Privacy Models
We study the problem of privately computing the anonymized histogram (a. k. a.
Private Isotonic Regression
For the most general problem of isotonic regression over a partially ordered set (poset) $\mathcal{X}$ and for any Lipschitz loss function, we obtain a pure-DP algorithm that, given $n$ input points, has an expected excess empirical risk of roughly $\mathrm{width}(\mathcal{X}) \cdot \log|\mathcal{X}| / n$, where $\mathrm{width}(\mathcal{X})$ is the width of the poset.
Private Ad Modeling with DP-SGD
A well-known algorithm in privacy-preserving ML is differentially private stochastic gradient descent (DP-SGD).
Regression with Label Differential Privacy
We study the task of training regression models with the guarantee of label differential privacy (DP).
Revenue Management without Demand Forecasting: A Data-Driven Approach for Bid Price Generation
We develop a methodology to generate bid prices using historical booking data only.
On User-Level Private Convex Optimization
We introduce a new mechanism for stochastic convex optimization (SCO) with user-level differential privacy guarantees.
Approximating a RUM from Distributions on k-Slates
In this work we consider the problem of fitting Random Utility Models (RUMs) to user choices.
Ticketed Learning-Unlearning Schemes
Subsequently, given any subset of examples that wish to be unlearnt, the goal is to learn, without the knowledge of the original training dataset, a good predictor that is identical to the predictor that would have been produced when learning from scratch on the surviving examples.
Optimal Unbiased Randomizers for Regression with Label Differential Privacy
We propose a new family of label randomizers for training regression models under the constraint of label differential privacy (DP).
Training Differentially Private Ad Prediction Models with Semi-Sensitive Features
Motivated by problems arising in digital advertising, we introduce the task of training differentially private (DP) machine learning models with semi-sensitive features.
How Private is DP-SGD?
We demonstrate a substantial gap between the privacy guarantees of the Adaptive Batch Linear Queries (ABLQ) mechanism under different types of batch sampling: (i) Shuffling, and (ii) Poisson subsampling; the typical analysis of Differentially Private Stochastic Gradient Descent (DP-SGD) follows by interpreting it as a post-processing of ABLQ.
Differentially Private Optimization with Sparse Gradients
Motivated by applications of large embedding models, we study differentially private (DP) optimization problems under sparsity of individual gradients.
