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.
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 • 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 • 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 • 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 • 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.
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 • 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 • 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 • 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 • 3 May 2022 • Pranjal Awasthi, Nishanth Dikkala, Pritish Kamath
Recent investigations in noise contrastive estimation suggest, both empirically as well as theoretically, that while having more "negative samples" in the contrastive loss improves downstream classification performance initially, beyond a threshold, it hurts downstream performance due to a "collision-coverage" trade-off.
no code implementations • NeurIPS 2021 • Emmanuel Abbe, Pritish Kamath, Eran Malach, Colin Sandon, Nathan Srebro
With fine enough precision relative to minibatch size, namely when $b \rho$ is small enough, SGD can go beyond SQ learning and simulate any sample-based learning algorithm and thus its learning power is equivalent to that of PAC learning; this extends prior work that achieved this result for $b=1$.
no code implementations • 6 Jul 2021 • Ankit Shah, Pritish Kamath, Shen Li, Patrick Craven, Kevin Landers, Kevin Oden, Julie Shah
When observing task demonstrations, human apprentices are able to identify whether a given task is executed correctly long before they gain expertise in actually performing that task.
no code implementations • 14 Apr 2021 • Gene Li, Pritish Kamath, Dylan J. Foster, Nathan Srebro
We provide new insights on eluder dimension, a complexity measure that has been extensively used to bound the regret of algorithms for online bandits and reinforcement learning with function approximation.
no code implementations • 1 Mar 2021 • Eran Malach, Pritish Kamath, Emmanuel Abbe, Nathan Srebro
Complementing this, we show that without these conditions, gradient descent can in fact learn with small error even when no kernel method, in particular using the tangent kernel, can achieve a non-trivial advantage over random guessing.
no code implementations • 4 Jan 2021 • Pritish Kamath, Akilesh Tangella, Danica J. Sutherland, Nathan Srebro
We show that the Invariant Risk Minimization (IRM) formulation of Arjovsky et al. (2019) can fail to capture "natural" invariances, at least when used in its practical "linear" form, and even on very simple problems which directly follow the motivating examples for IRM.
no code implementations • 9 Mar 2020 • Pritish Kamath, Omar Montasser, Nathan Srebro
We present and study approximate notions of dimensional and margin complexity, which correspond to the minimal dimension or norm of an embedding required to approximate, rather then exactly represent, a given hypothesis class.
no code implementations • NeurIPS 2018 • Ankit Shah, Pritish Kamath, Julie A. Shah, Shen Li
When observing task demonstrations, human apprentices are able to identify whether a given task is executed correctly long before they gain expertise in actually performing that task.
1 code implementation • 4 Dec 2016 • Mohammad Bavarian, Badih Ghazi, Elad Haramaty, Pritish Kamath, Ronald L. Rivest, Madhu Sudan
In this note, we give a surprisingly simple proof that this protocol is in fact tight.
Computational Complexity Information Theory Information Theory