Search Results for author:
Found 22 papers, 4 papers with code
Multi-Task Differential Privacy Under Distribution Skew
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.
Differentially Private Image Classification from Features
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 #29 on
Image Classification
on ImageNet
(using extra training data)
Reciprocity in Machine Learning
Are these contributions (outflows of influence) and benefits (inflows of influence) reciprocal?
ALX: Large Scale Matrix Factorization on TPUs
We present ALX, an open-source library for distributed matrix factorization using Alternating Least Squares, written in JAX.
Revisiting the Performance of iALS on Item Recommendation Benchmarks
Matrix factorization learned by implicit alternating least squares (iALS) is a popular baseline in recommender system research publications.
iALS++: Speeding up Matrix Factorization with Subspace Optimization
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.
Private Alternating Least Squares: Practical Private Matrix Completion with Tighter Rates
We study the problem of differentially private (DP) matrix completion under user-level privacy.
Rankmax: An Adaptive Projection Alternative to the Softmax Function
Several machine learning models involve mapping a score vector to a probability vector.
Global Convergence of Second-order Dynamics in Two-layer Neural Networks
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.
Neural Collaborative Filtering vs. Matrix Factorization Revisited
This approach is often referred to as neural collaborative filtering (NCF).
Ranked #6 on
Link Prediction
on Yelp
Superbloom: Bloom filter meets Transformer
We extend the idea of word pieces in natural language models to machine learning tasks on opaque ids.
Scaling Up Collaborative Filtering Data Sets through Randomized Fractal Expansions
Recommender system research suffers from a disconnect between the size of academic data sets and the scale of industrial production systems.
Scalable Realistic Recommendation Datasets through Fractal Expansions
A larger version features 655 billion ratings, 7 million items and 17 million users.
Efficient Training on Very Large Corpora via Gramian Estimation
We study the problem of learning similarity functions over very large corpora using neural network embedding models.
Acceleration and Averaging in Stochastic Descent Dynamics
We formulate and study a general family of (continuous-time) stochastic dynamics for accelerated first-order minimization of smooth convex functions.
Acceleration and Averaging in Stochastic Mirror Descent Dynamics
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.
Minimizing Regret on Reflexive Banach Spaces and Nash Equilibria in Continuous Zero-Sum Games
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.
Adaptive Averaging in Accelerated Descent Dynamics
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 $w(t)$.
Minimizing Regret on Reflexive Banach Spaces and Learning Nash Equilibria in Continuous Zero-Sum Games
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 $p > 1$.
Accelerated Mirror Descent in Continuous and Discrete Time
We study accelerated mirror descent dynamics in continuous and discrete time.
Dual Averaging on Compactly-Supported Distributions And Application to No-Regret Learning on a Continuum
We consider an online learning problem on a continuum.
Learning Nash Equilibria in Congestion Games
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.
