Search Results for author:
Found 67 papers, 14 papers with code
Robust Pricing in Dynamic Mechanism Design
Motivated by the repeated sale of online ads via auctions, optimal pricing in repeated auctions has attracted a large body of research.
TeraHAC: Hierarchical Agglomerative Clustering of Trillion-Edge Graphs
Our algorithm is based on a new approach to computing $(1+\epsilon)$-approximate HAC, which is a novel combination of the nearest-neighbor chain algorithm and the notion of $(1+\epsilon)$-approximate HAC.
Causal Inference with Differentially Private (Clustered) Outcomes
Estimating causal effects from randomized experiments is only feasible if participants agree to reveal their potentially sensitive responses.
Causal Estimation of User Learning in Personalized Systems
In online platforms, the impact of a treatment on an observed outcome may change over time as 1) users learn about the intervention, and 2) the system personalization, such as individualized recommendations, change over time.
Learning across Data Owners with Joint Differential Privacy
In this paper, we study the setting in which data owners train machine learning models collaboratively under a privacy notion called joint differential privacy [Kearns et al., 2018].
Learning from Aggregated Data: Curated Bags versus Random Bags
Our method is based on the observation that the sum of the gradients of the loss function on individual data examples in a curated bag can be computed from the aggregate label without the need for individual labels.
Robust and differentially private stochastic linear bandits
In this paper, we study the stochastic linear bandit problem under the additional requirements of differential privacy, robustness and batched observations.
Measuring Re-identification Risk
In this work, we present a new theoretical framework to measure re-identification risk in such user representations.
Learning Rate Schedules in the Presence of Distribution Shift
We design learning rate schedules that minimize regret for SGD-based online learning in the presence of a changing data distribution.
Replicable Clustering
We design replicable algorithms in the context of statistical clustering under the recently introduced notion of replicability from Impagliazzo et al. [2022].
Approximately Optimal Core Shapes for Tensor Decompositions
This work studies the combinatorial optimization problem of finding an optimal core tensor shape, also called multilinear rank, for a size-constrained Tucker decomposition.
Robust Budget Pacing with a Single Sample
Given the inherent non-stationarity in an advertiser's value and also competing advertisers' values over time, a commonly used approach is to learn a target expenditure plan that specifies a target spend as a function of time, and then run a controller that tracks this plan.
Multi-channel Autobidding with Budget and ROI Constraints
In light of this finding, under a bandit feedback setting that mimics real-world scenarios where advertisers have limited information on ad auctions in each channels and how channels procure ads, we present an efficient learning algorithm that produces per-channel budgets whose resulting conversion approximates that of the global optimal problem.
Differentially-Private Hierarchical Clustering with Provable Approximation Guarantees
Then, we exhibit a polynomial-time approximation algorithm with $O(|V|^{2. 5}/ \epsilon)$-additive error, and an exponential-time algorithm that meets the lower bound.
Constant Approximation for Normalized Modularity and Associations Clustering
We study the problem of graph clustering under a broad class of objectives in which the quality of a cluster is defined based on the ratio between the number of edges in the cluster, and the total weight of vertices in the cluster.
Stars: Tera-Scale Graph Building for Clustering and Graph Learning
We evaluate the performance of Stars for clustering and graph learning, and demonstrate 10~1000-fold improvements in pairwise similarity comparisons compared to different baselines, and 2~10-fold improvement in running time without quality loss.
Anonymous Bandits for Multi-User Systems
In this work, we present and study a new framework for online learning in systems with multiple users that provide user anonymity.
Replicable Bandits
Similarly, for stochastic linear bandits (with finitely and infinitely many arms) we develop replicable policies that achieve the best-known problem-independent regret bounds with an optimal dependency on the replicability parameter.
Sequential Attention for Feature Selection
Feature selection is the problem of selecting a subset of features for a machine learning model that maximizes model quality subject to a budget constraint.
Differentially Private Graph Learning via Sensitivity-Bounded Personalized PageRank
Personalized PageRank (PPR) is a fundamental tool in unsupervised learning of graph representations such as node ranking, labeling, and graph embedding.
Smooth Anonymity for Sparse Binary Matrices
When working with user data providing well-defined privacy guarantees is paramount.
TF-GNN: Graph Neural Networks in TensorFlow
TensorFlow-GNN (TF-GNN) is a scalable library for Graph Neural Networks in TensorFlow.
Scalable Differentially Private Clustering via Hierarchically Separated Trees
We study the private $k$-median and $k$-means clustering problem in $d$ dimensional Euclidean space.
Tackling Provably Hard Representative Selection via Graph Neural Networks
Representative Selection (RS) is the problem of finding a small subset of exemplars from a dataset that is representative of the dataset.
Improved Approximations for Euclidean $k$-means and $k$-median, via Nested Quasi-Independent Sets
Motivated by data analysis and machine learning applications, we consider the popular high-dimensional Euclidean $k$-median and $k$-means problems.
On Dual-Based PI Controllers for Online Allocation Problems
This paper provides the first regret bounds on the performance of dual-based PI controllers for online allocation problems.
Synthetic Design: An Optimization Approach to Experimental Design with Synthetic Controls
We investigate the optimal design of experimental studies that have pre-treatment outcome data available.
Tight and Robust Private Mean Estimation with Few Users
In particular, we provide a nearly optimal trade-off between the number of users and the number of samples per user required for private mean estimation, even when the number of users is as low as $O(\frac{1}{\varepsilon}\log\frac{1}{\delta})$.
Label differential privacy via clustering
We present new mechanisms for \emph{label differential privacy}, a relaxation of differentially private machine learning that only protects the privacy of the labels in the training set.
Scalable Community Detection via Parallel Correlation Clustering
Our empirical evaluation shows that this framework improves the state-of-the-art trade-offs between speed and quality of scalable community detection.
Almost Tight Approximation Algorithms for Explainable Clustering
Next, we study the $k$-means problem in this context and provide an $O(k \log k)$-approximation algorithm for explainable $k$-means, improving over the $O(k^2)$ bound of Dasgupta et al. and the $O(d k \log k)$ bound of \cite{laber2021explainable}.
Hierarchical Agglomerative Graph Clustering in Nearly-Linear Time
For this variant, this is the first exact algorithm that runs in subquadratic time, as long as $m=n^{2-\epsilon}$ for some constant $\epsilon > 0$.
Parallelizing Thompson Sampling
How can we make use of information parallelism in online decision making problems while efficiently balancing the exploration-exploitation trade-off?
Batched Neural Bandits
In many sequential decision-making problems, the individuals are split into several batches and the decision-maker is only allowed to change her policy at the end of batches.
Contextual Reserve Price Optimization in Auctions via Mixed Integer Programming
Moreover, we show that this MIP formulation is ideal (i. e. the strongest possible formulation) for the revenue function of a single impression.
Smoothly Bounding User Contributions in Differential Privacy
But at the same time, more noise might need to be added to the algorithm in order to keep the algorithm differentially private and this might hurt the algorithm’s performance.
Optimal Approximation - Smoothness Tradeoffs for Soft-Max Functions
A soft-max function has two main efficiency measures: (1) approximation - which corresponds to how well it approximates the maximum function, (2) smoothness - which shows how sensitive it is to changes of its input.
The Best of Many Worlds: Dual Mirror Descent for Online Allocation Problems
In this paper, we consider a data-driven setting in which the reward and resource consumption of each request are generated using an input model that is unknown to the decision maker.
Optimal Approximation -- Smoothness Tradeoffs for Soft-Max Functions
A soft-max function has two main efficiency measures: (1) approximation - which corresponds to how well it approximates the maximum function, (2) smoothness - which shows how sensitive it is to changes of its input.
Limiting Behaviors of Nonconvex-Nonconcave Minimax Optimization via Continuous-Time Systems
Unlike nonconvex optimization, where gradient descent is guaranteed to converge to a local optimizer, algorithms for nonconvex-nonconcave minimax optimization can have topologically different solution paths: sometimes converging to a solution, sometimes never converging and instead following a limit cycle, and sometimes diverging.
Regularized Online Allocation Problems: Fairness and Beyond
In this paper, we introduce the \emph{regularized online allocation problem}, a variant that includes a non-linear regularizer acting on the total resource consumption.
The Landscape of the Proximal Point Method for Nonconvex-Nonconcave Minimax Optimization
Critically, we show this envelope not only smooths the objective but can convexify and concavify it based on the level of interaction present between the minimizing and maximizing variables.
Bandits with adversarial scaling
We study "adversarial scaling", a multi-armed bandit model where rewards have a stochastic and an adversarial component.
Dynamic Incentive-aware Learning: Robust Pricing in Contextual Auctions
Motivated by pricing in ad exchange markets, we consider the problem of robust learning of reserve prices against strategic buyers in repeated contextual second-price auctions.
Dual Mirror Descent for Online Allocation Problems
The revenue function and resource consumption of each request are drawn independently and at random from a probability distribution that is unknown to the decision maker.
Optimization and Control
Contextual Reserve Price Optimization in Auctions via Mixed-Integer Programming
Moreover, we show that this MIP formulation is ideal (i. e. the strongest possible formulation) for the revenue function of a single impression.
A Robust Non-Clairvoyant Dynamic Mechanism for Contextual Auctions
Dynamic mechanisms offer powerful techniques to improve on both revenue and efficiency by linking sequential auctions using state information, but these techniques rely on exact distributional information of the buyers’ valuations (present and future), which limits their use in learning settings.
Variance Reduction in Bipartite Experiments through Correlation Clustering
This paper introduces a novel clustering objective and a corresponding algorithm that partitions a bipartite graph so as to maximize the statistical power of a bipartite experiment on that graph.
Adaptivity in Adaptive Submodularity
We propose an efficient semi adaptive policy that with $O(\log n \times\log k)$ adaptive rounds of observations can achieve an almost tight $1-1/e-\epsilon$ approximation guarantee with respect to an optimal policy that carries out $k$ actions in a fully sequential manner.
Regret Bounds for Batched Bandits
We present simple and efficient algorithms for the batched stochastic multi-armed bandit and batched stochastic linear bandit problems.
Accelerating Gradient Boosting Machine
This is the first GBM type of algorithm with theoretically-justified accelerated convergence rate.
Approximate Leave-One-Out for High-Dimensional Non-Differentiable Learning Problems
$\mathcal{C} \subset \mathbb{R}^{p}$ is a closed convex set.
Contextual Bandits with Cross-learning
We consider the variant of this problem where in addition to receiving the reward $r_{i, t}(c)$, the learner also learns the values of $r_{i, t}(c')$ for some other contexts $c'$ in set $\mathcal{O}_i(c)$; i. e., the rewards that would have been achieved by performing that action under different contexts $c'\in \mathcal{O}_i(c)$.
Parallel and Streaming Algorithms for K-Core Decomposition
The $k$-core decomposition is a fundamental primitive in many machine learning and data mining applications.
Approximate Leave-One-Out for Fast Parameter Tuning in High Dimensions
Consider the following class of learning schemes: $$\hat{\boldsymbol{\beta}} := \arg\min_{\boldsymbol{\beta}}\;\sum_{j=1}^n \ell(\boldsymbol{x}_j^\top\boldsymbol{\beta}; y_j) + \lambda R(\boldsymbol{\beta}),\qquad\qquad (1) $$ where $\boldsymbol{x}_i \in \mathbb{R}^p$ and $y_i \in \mathbb{R}$ denote the $i^{\text{th}}$ feature and response variable respectively.
Proportional Allocation: Simple, Distributed, and Diverse Matching with High Entropy
Inspired by many applications of bipartite matching in online advertising and machine learning, we study a simple and natural iterative proportional allocation algorithm: Maintain a priority score $\priority_a$ for each node $a\in \mathds{A}$ on one side of the bipartition, initialized as $\priority_a=1$.
Accelerating Greedy Coordinate Descent Methods
On the empirical side, while both AGCD and ASCD outperform Accelerated Randomized Coordinate Descent on most instances in our numerical experiments, we note that AGCD significantly outperforms the other two methods in our experiments, in spite of a lack of theoretical guarantees for this method.
Stochastic bandits robust to adversarial corruptions
We introduce a new model of stochastic bandits with adversarial corruptions which aims to capture settings where most of the input follows a stochastic pattern but some fraction of it can be adversarially changed to trick the algorithm, e. g., click fraud, fake reviews and email spam.
Dynamic Revenue Sharing
In this paper, we characterize the optimal revenue sharing scheme that satisfies both constraints in expectation.
Affinity Clustering: Hierarchical Clustering at Scale
In particular, we propose affinity, a novel hierarchical clustering based on Boruvka's MST algorithm.
Matroids Hitting Sets and Unsupervised Dependency Grammar Induction
This paper formulates a novel problem on graphs: find the minimal subset of edges in a fully connected graph, such that the resulting graph contains all spanning trees for a set of specifed sub-graphs.
Linear Relaxations for Finding Diverse Elements in Metric Spaces
We first study the approximation quality of the algorithm by comparing with the LP objective.
Bi-Objective Online Matching and Submodular Allocations
In particular, in online advertising it is fairly common to optimize multiple metrics, such as clicks, conversions, and impressions, as well as other metrics which may be largely uncorrelated such as ‘share of voice’, and ‘buyer surplus’.
Consistent Hashing with Bounded Loads
Designing algorithms for balanced allocation of clients to servers in dynamic settings is a challenging problem for a variety of reasons.
Data Structures and Algorithms
Tight Bounds for Approximate Carathéodory and Beyond
We give a deterministic nearly-linear time algorithm for approximating any point inside a convex polytope with a sparse convex combination of the polytope's vertices.
Distributed Balanced Clustering via Mapping Coresets
Large-scale clustering of data points in metric spaces is an important problem in mining big data sets.
Local Graph Clustering Beyond Cheeger's Inequality
We also prove that our analysis is tight, and perform empirical evaluation to support our theory on both synthetic and real data.
