1 code implementation • 6 Feb 2020 • Sara Ahmadian, Alessandro Epasto, Ravi Kumar, Mohammad Mahdian
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.
2 code implementations • NeurIPS 2017 • Flavio Chierichetti, Ravi Kumar, Silvio Lattanzi, Sergei Vassilvitskii
We show that any fair clustering problem can be decomposed into first finding good fairlets, and then using existing machinery for traditional clustering algorithms.
3 code implementations • 29 Mar 2012 • Bahman Bahmani, Benjamin Moseley, Andrea Vattani, Ravi Kumar, Sergei Vassilvitskii
The recently proposed k-means++ initialization algorithm achieves this, obtaining an initial set of centers that is provably close to the optimum solution.
Databases
1 code implementation • 5 Apr 2017 • Ravi Kumar, Maithra Raghu, Tamas Sarlos, Andrew Tomkins
We introduce LAMP: the Linear Additive Markov Process.
no code implementations • NAACL 2016 • Justine Zhang, Ravi Kumar, Sujith Ravi, Cristian Danescu-Niculescu-Mizil
Public debates are a common platform for presenting and juxtaposing diverging views on important issues.
no code implementations • NeurIPS 2018 • Flavio Chierichetti, Anirban Dasgupta, Shahrzad Haddadan, Ravi Kumar, Silvio Lattanzi
The classic Mallows model is a widely-used tool to realize distributions on per- mutations.
no code implementations • NeurIPS 2018 • Manish Purohit, Zoya Svitkina, Ravi Kumar
In this work we study the problem of using machine-learned predictions to improve performance of online algorithms.
no code implementations • NeurIPS 2016 • Rishi Gupta, Ravi Kumar, Sergei Vassilvitskii
We study the problem of reconstructing a mixture of Markov chains from the trajectories generated by random walks through the state space.
no code implementations • NeurIPS 2012 • Abhimanyu Das, Anirban Dasgupta, Ravi Kumar
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.
no code implementations • NeurIPS 2008 • Deepayan Chakrabarti, Ravi Kumar, Filip Radlinski, Eli Upfal
In our model, arms have (stochastic) lifetime after which they expire.
no code implementations • ICML 2017 • Flavio Chierichetti, Sreenivas Gollapudi, Ravi Kumar, Silvio Lattanzi, Rina Panigrahy, David P. Woodruff
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.
no code implementations • ICML 2018 • Flavio Chierichetti, Ravi Kumar, Andrew Tomkins
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.
no code implementations • 8 Apr 2019 • Abhimanyu Das, Sreenivas Gollapudi, Ravi Kumar, Rina Panigrahy
In this paper we study the learnability of deep random networks from both theoretical and practical points of view.
no code implementations • 29 May 2019 • Sara Ahmadian, Alessandro Epasto, Ravi Kumar, Mohammad Mahdian
In this paper we consider clustering problems in which each point is endowed with a color.
no code implementations • 6 Jul 2019 • Maryam Aliakbarpour, Ravi Kumar, Ronitt Rubinfeld
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.
no code implementations • 29 Aug 2019 • Badih Ghazi, Noah Golowich, Ravi Kumar, Rasmus Pagh, Ameya Velingker
- 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.
no code implementations • 24 Oct 2019 • Benjamin Spector, Ravi Kumar, Andrew Tomkins
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.
no code implementations • NeurIPS 2019 • Ravi Kumar, Manish Purohit, Zoya Svitkina, Erik Vee, Joshua Wang
When training complex neural networks, memory usage can be an important bottleneck.
no code implementations • ICML 2020 • Aditya Bhaskara, Ashok Cutkosky, Ravi Kumar, Manish Purohit
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.
no code implementations • NeurIPS 2020 • Sara Ahmadian, Alessandro Epasto, Marina Knittel, Ravi Kumar, Mohammad Mahdian, Benjamin Moseley, Philip Pham, Sergei Vassilvitskii, Yuyan Wang
As machine learning has become more prevalent, researchers have begun to recognize the necessity of ensuring machine learning systems are fair.
no code implementations • 7 Jul 2020 • Badih Ghazi, Noah Golowich, Ravi Kumar, Pasin Manurangsi
We study closure properties for the Littlestone and threshold dimensions of binary hypothesis classes.
no code implementations • NeurIPS 2020 • Badih Ghazi, Ravi Kumar, Pasin Manurangsi
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.
no code implementations • 21 Sep 2020 • Lijie Chen, Badih Ghazi, Ravi Kumar, Pasin Manurangsi
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 $n$.
1 code implementation • 3 Apr 2020 • Andrei Z. Broder, Ravi Kumar
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
no code implementations • 6 Oct 2020 • Flavio Chierichetti, Anirban Dasgupta, Ravi Kumar
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.
no code implementations • NeurIPS 2020 • Aditya Bhaskara, Ashok Cutkosky, Ravi Kumar, Manish Purohit
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.
no code implementations • 30 Nov 2020 • Badih Ghazi, Ravi Kumar, Pasin Manurangsi, Thao Nguyen
In this work, we study the trade-off between differential privacy and adversarial robustness under L2-perturbations in the context of learning halfspaces.
no code implementations • 7 Dec 2020 • Badih Ghazi, Noah Golowich, Ravi Kumar, Pasin Manurangsi
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.
no code implementations • 16 Dec 2020 • Badih Ghazi, Ravi Kumar, Pasin Manurangsi
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.
no code implementations • NeurIPS 2021 • Badih Ghazi, Noah Golowich, Ravi Kumar, Pasin Manurangsi, Chiyuan Zhang
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.
no code implementations • 17 Feb 2021 • Prateek Bhadauria, Ravi Kumar, Sanjay Sharma
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.
no code implementations • 20 Apr 2021 • Alisa Chang, Badih Ghazi, Ravi Kumar, Pasin Manurangsi
We provide an approximation algorithm for k-means clustering in the one-round (aka non-interactive) local model of differential privacy (DP).
no code implementations • 3 Aug 2021 • Rohan Anil, Badih Ghazi, Vineet Gupta, Ravi Kumar, Pasin Manurangsi
In this work, we study the large-scale pretraining of BERT-Large with differentially private SGD (DP-SGD).
no code implementations • 21 Oct 2021 • Badih Ghazi, Ravi Kumar, Pasin Manurangsi
Most works in learning with differential privacy (DP) have focused on the setting where each user has a single sample.
no code implementations • NeurIPS 2021 • Aditya Bhaskara, Ashok Cutkosky, Ravi Kumar, Manish Purohit
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.
no code implementations • NeurIPS 2021 • Sungjin Im, Ravi Kumar, Mahshid Montazer Qaem, Manish Purohit
There has been recent interest in using machine-learned predictions to improve the worst-case guarantees of online algorithms.
no code implementations • NeurIPS 2021 • Badih Ghazi, Ravi Kumar, Pasin Manurangsi
Most works in learning with differential privacy (DP) have focused on the setting where each user has a single sample.
no code implementations • 9 Feb 2022 • Sungjin Im, Ravi Kumar, Aditya Petety, Manish Purohit
Learning-augmented algorithms -- in which, traditional algorithms are augmented with machine-learned predictions -- have emerged as a framework to go beyond worst-case analysis.
no code implementations • 4 May 2022 • Ravi Kumar, Shahin Boluki, Karl Isler, Jonas Rauch, Darius Walczak
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.
no code implementations • 10 Jul 2022 • Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi
We introduce a new algorithm for numerical composition of privacy random variables, useful for computing the accurate differential privacy parameters for composition of mechanisms.
no code implementations • 10 Jul 2022 • Vadym Doroshenko, Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi
The privacy loss distribution (PLD) provides a tight characterization of the privacy loss of a mechanism in the context of differential privacy (DP).
no code implementations • 16 Aug 2022 • Priya Mehta, Sandeep Kumar, Ravi Kumar, Ch. Sobhan Babu
To validate the proposed approach, we train a BiGAN with the proposed training approach to detect taxpayers, who are manipulating their tax returns.
no code implementations • 8 Sep 2022 • Badih Ghazi, Ravi Kumar, Pasin Manurangsi, Thomas Steinke
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.
no code implementations • 27 Oct 2022 • Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi
We study the problem of privately computing the anonymized histogram (a. k. a.
no code implementations • 27 Oct 2022 • Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi
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.
no code implementations • 21 Nov 2022 • Carson Denison, Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Krishna Giri Narra, Amer Sinha, Avinash V Varadarajan, Chiyuan Zhang
A well-known algorithm in privacy-preserving ML is differentially private stochastic gradient descent (DP-SGD).
no code implementations • 12 Dec 2022 • Badih Ghazi, Pritish Kamath, Ravi Kumar, Ethan Leeman, Pasin Manurangsi, Avinash V Varadarajan, Chiyuan Zhang
We study the task of training regression models with the guarantee of label differential privacy (DP).
no code implementations • 14 Apr 2023 • Ezgi C. Eren, Zhaoyang Zhang, Jonas Rauch, Ravi Kumar, Royce Kallesen
We develop a methodology to generate bid prices using historical booking data only.
no code implementations • 8 May 2023 • Badih Ghazi, Pritish Kamath, Ravi Kumar, Raghu Meka, Pasin Manurangsi, Chiyuan Zhang
We introduce a new mechanism for stochastic convex optimization (SCO) with user-level differential privacy guarantees.
1 code implementation • 22 May 2023 • Flavio Chierichetti, Mirko Giacchini, Ravi Kumar, Alessandro Panconesi, Andrew Tomkins
In this work we consider the problem of fitting Random Utility Models (RUMs) to user choices.
no code implementations • 27 Jun 2023 • Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Ayush Sekhari, Chiyuan Zhang
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.
no code implementations • NeurIPS 2023 • Ashwinkumar Badanidiyuru, Badih Ghazi, Pritish Kamath, Ravi Kumar, Ethan Leeman, Pasin Manurangsi, Avinash V Varadarajan, Chiyuan Zhang
We propose a new family of label randomizers for training regression models under the constraint of label differential privacy (DP).
no code implementations • 26 Jan 2024 • Lynn Chua, Qiliang Cui, Badih Ghazi, Charlie Harrison, Pritish Kamath, Walid Krichene, Ravi Kumar, Pasin Manurangsi, Krishna Giri Narra, Amer Sinha, Avinash Varadarajan, Chiyuan Zhang
Motivated by problems arising in digital advertising, we introduce the task of training differentially private (DP) machine learning models with semi-sensitive features.
no code implementations • 26 Mar 2024 • Lynn Chua, Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Amer Sinha, Chiyuan Zhang
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.
no code implementations • 16 Apr 2024 • Badih Ghazi, Cristóbal Guzmán, Pritish Kamath, Ravi Kumar, Pasin Manurangsi
Motivated by applications of large embedding models, we study differentially private (DP) optimization problems under sparsity of individual gradients.