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 • 24 Oct 2023 • Walid Krichene, Nicolas Mayoraz, Steffen Rendle, Shuang Song, Abhradeep Thakurta, Li Zhang

We study a class of private learning problems in which the data is a join of private and public features.

no code implementations • 17 Sep 2023 • Mihaela Curmei, Walid Krichene, Li Zhang, Mukund Sundararajan

It can be applied to different types of public item data, including: (1) categorical item features; (2) item-item similarities learned from public sources; and (3) publicly available user feedback.

no code implementations • 15 Feb 2023 • Walid Krichene, Prateek Jain, Shuang Song, Mukund Sundararajan, Abhradeep Thakurta, Li Zhang

We study the problem of multi-task learning under user-level differential privacy, in which $n$ users contribute data to $m$ tasks, each involving a subset of users.

1 code implementation • 24 Nov 2022 • Harsh Mehta, Walid Krichene, Abhradeep Thakurta, Alexey Kurakin, Ashok Cutkosky

We find that linear regression is much more effective than logistic regression from both privacy and computational aspects, especially at stricter epsilon values ($\epsilon < 1$).

Ranked #33 on Image Classification on ImageNet

no code implementations • 19 Feb 2022 • Mukund Sundararajan, Walid Krichene

Are these contributions (outflows of influence) and benefits (inflows of influence) reciprocal?

no code implementations • 3 Dec 2021 • Harsh Mehta, Steffen Rendle, Walid Krichene, Li Zhang

We present ALX, an open-source library for distributed matrix factorization using Alternating Least Squares, written in JAX.

1 code implementation • 26 Oct 2021 • Steffen Rendle, Walid Krichene, Li Zhang, Yehuda Koren

Matrix factorization learned by implicit alternating least squares (iALS) is a popular baseline in recommender system research publications.

1 code implementation • 26 Oct 2021 • Steffen Rendle, Walid Krichene, Li Zhang, Yehuda Koren

However, iALS does not scale well with large embedding dimensions, d, due to its cubic runtime dependency on d. Coordinate descent variations, iCD, have been proposed to lower the complexity to quadratic in d. In this work, we show that iCD approaches are not well suited for modern processors and can be an order of magnitude slower than a careful iALS implementation for small to mid scale embedding sizes (d ~ 100) and only perform better than iALS on large embeddings d ~ 1000.

no code implementations • 20 Jul 2021 • Steve Chien, Prateek Jain, Walid Krichene, Steffen Rendle, Shuang Song, Abhradeep Thakurta, Li Zhang

We study the problem of differentially private (DP) matrix completion under user-level privacy.

no code implementations • NeurIPS 2020 • Weiwei Kong, Walid Krichene, Nicolas Mayoraz, Steffen Rendle, Li Zhang

Several machine learning models involve mapping a score vector to a probability vector.

no code implementations • 14 Jul 2020 • Walid Krichene, Kenneth F. Caluya, Abhishek Halder

Recent results have shown that for two-layer fully connected neural networks, gradient flow converges to a global optimum in the infinite width limit, by making a connection between the mean field dynamics and the Wasserstein gradient flow.

4 code implementations • 19 May 2020 • Steffen Rendle, Walid Krichene, Li Zhang, John Anderson

This approach is often referred to as neural collaborative filtering (NCF).

Ranked #6 on Link Prediction on Yelp

no code implementations • 11 Feb 2020 • John Anderson, Qingqing Huang, Walid Krichene, Steffen Rendle, Li Zhang

We extend the idea of word pieces in natural language models to machine learning tasks on opaque ids.

no code implementations • 8 Apr 2019 • Francois Belletti, Karthik Lakshmanan, Walid Krichene, Nicolas Mayoraz, Yi-fan Chen, John Anderson, Taylor Robie, Tayo Oguntebi, Dan Shirron, Amit Bleiwess

Recommender system research suffers from a disconnect between the size of academic data sets and the scale of industrial production systems.

1 code implementation • 23 Jan 2019 • Francois Belletti, Karthik Lakshmanan, Walid Krichene, Yi-fan Chen, John Anderson

A larger version features 655 billion ratings, 7 million items and 17 million users.

no code implementations • ICLR 2019 • Walid Krichene, Nicolas Mayoraz, Steffen Rendle, Li Zhang, Xinyang Yi, Lichan Hong, Ed Chi, John Anderson

We study the problem of learning similarity functions over very large corpora using neural network embedding models.

no code implementations • NeurIPS 2017 • Walid Krichene, Peter L. Bartlett

We formulate and study a general family of (continuous-time) stochastic dynamics for accelerated first-order minimization of smooth convex functions.

no code implementations • 19 Jul 2017 • Walid Krichene, Peter L. Bartlett

We discuss the interaction between the parameters of the dynamics (learning rate and averaging weights) and the covariation of the noise process, and show, in particular, how the asymptotic rate of covariation affects the choice of parameters and, ultimately, the convergence rate.

no code implementations • NeurIPS 2016 • Walid Krichene, Alexandre Bayen, Peter L. Bartlett

This dynamics can be described naturally as a coupling of a dual variable accumulating gradients at a given rate $\eta(t)$, and a primal variable obtained as the weighted average of the mirrored dual trajectory, with weights $w(t)$.

no code implementations • NeurIPS 2016 • Maximilian Balandat, Walid Krichene, Claire Tomlin, Alexandre Bayen

We study a general adversarial online learning problem, in which we are given a decision set X' in a reflexive Banach space X and a sequence of reward vectors in the dual space of X.

no code implementations • 3 Jun 2016 • Maximilian Balandat, Walid Krichene, Claire Tomlin, Alexandre Bayen

Under the assumption of uniformly continuous rewards, we obtain explicit anytime regret bounds in a setting where the decision set is the set of probability distributions on a compact metric space $S$ whose Radon-Nikodym derivatives are elements of $L^p(S)$ for some $p > 1$.

no code implementations • NeurIPS 2015 • Walid Krichene, Alexandre Bayen, Peter L. Bartlett

We study accelerated mirror descent dynamics in continuous and discrete time.

no code implementations • 29 Apr 2015 • Walid Krichene

We consider an online learning problem on a continuum.

no code implementations • 31 Jul 2014 • Walid Krichene, Benjamin Drighès, Alexandre M. Bayen

We show that strong convergence can be guaranteed for a class of algorithms with a vanishing upper bound on discounted regret, and which satisfy an additional condition.

Cannot find the paper you are looking for? You can
Submit a new open access paper.

Contact us on:
hello@paperswithcode.com
.
Papers With Code is a free resource with all data licensed under CC-BY-SA.