Search Results for author:
Found 14 papers, 0 papers with code
Improved Online Learning Algorithms for CTR Prediction in Ad Auctions
In this work, we investigate the online learning problem of revenue maximization in ad auctions, where the seller needs to learn the click-through rates (CTRs) of each ad candidate and charge the price of the winner through a pay-per-click manner.
Mixtures of Gaussians are Privately Learnable with a Polynomial Number of Samples
We study the problem of estimating mixtures of Gaussians under the constraint of differential privacy (DP).
Polynomial Time and Private Learning of Unbounded Gaussian Mixture Models
We study the problem of privately estimating the parameters of $d$-dimensional Gaussian Mixture Models (GMMs) with $k$ components.
User Response in Ad Auctions: An MDP Formulation of Long-Term Revenue Optimization
We propose a new Markov Decision Process (MDP) model for ad auctions to capture the user response to the quality of ads, with the objective of maximizing the long-term discounted revenue.
Continuous Prediction with Experts' Advice
Finally, we design an anytime continuous-time algorithm with regret matching the optimal fixed-time rate when the gains are independent Brownian Motions; in many settings, this is the most difficult case.
Private and polynomial time algorithms for learning Gaussians and beyond
As another application of our framework, we provide the first polynomial time $(\varepsilon, \delta)$-DP algorithm for robust learning of (unrestricted) Gaussians with sample complexity $\widetilde{O}(d^{3. 5})$.
Privately Learning Mixtures of Axis-Aligned Gaussians
We show that if $\mathcal{F}$ is privately list-decodable, then we can privately learn mixtures of distributions in $\mathcal{F}$.
Improved Algorithms for Online Submodular Maximization via First-order Regret Bounds
- For monotone submodular maximization subject to a matroid, we give an efficient algorithm which achieves a (1 − c/e − ε)-regret of O(√kT ln(n/k)) where n is the size of the ground set, k is the rank of the matroid, ε > 0 is a constant, and c is the average curvature.
Optimal anytime regret with two experts
In the fixed-time setting, where the time horizon is known in advance, algorithms that achieve the optimal regret are known when there are two, three, or four experts or when the number of experts is large.
Simple and optimal high-probability bounds for strongly-convex stochastic gradient descent
We consider a simple, non-uniform averaging strategy of Lacoste-Julien et al. (2011) and prove that it achieves the optimal $O(1/T)$ convergence rate with high probability.
A new dog learns old tricks: RL finds classic optimization algorithms
This paper introduces a novel framework for learning algorithms to solve online combinatorial optimization problems.
Tight Analyses for Non-Smooth Stochastic Gradient Descent
We prove that after $T$ steps of stochastic gradient descent, the error of the final iterate is $O(\log(T)/T)$ with high probability.
Nearly tight sample complexity bounds for learning mixtures of Gaussians via sample compression schemes
We prove that ϴ(k d^2 / ε^2) samples are necessary and sufficient for learning a mixture of k Gaussians in R^d, up to error ε in total variation distance.
Near-optimal Sample Complexity Bounds for Robust Learning of Gaussians Mixtures via Compression Schemes
We prove that $\tilde{\Theta}(k d^2 / \varepsilon^2)$ samples are necessary and sufficient for learning a mixture of $k$ Gaussians in $\mathbb{R}^d$, up to error $\varepsilon$ in total variation distance.
