Search Results for author:
Found 42 papers, 7 papers with code
Robust Feature Learning for Multi-Index Models in High Dimensions
Recently, there have been numerous studies on feature learning with neural networks, specifically on learning single- and multi-index models where the target is a function of a low-dimensional projection of the input.
Multi-Task Dynamic Pricing in Credit Market with Contextual Information
We show that the regret of our policy is better than both the policy that treats each security individually and the policy that treats all securities as the same.
Retraining with Predicted Hard Labels Provably Increases Model Accuracy
In this paper, we theoretically analyze retraining in a linearly separable setting with randomly corrupted labels given to us and prove that retraining can improve the population accuracy obtained by initially training with the given (noisy) labels.
Optimistic Rates for Learning from Label Proportions
We consider a weakly supervised learning problem called Learning from Label Proportions (LLP), where examples are grouped into ``bags'' and only the average label within each bag is revealed to the learner.
PriorBoost: An Adaptive Algorithm for Learning from Aggregate Responses
This work studies algorithms for learning from aggregate responses.
Learning from Aggregate responses: Instance Level versus Bag Level Loss Functions
In this paper, we study two natural loss functions for learning from aggregate responses: bag-level loss and the instance-level loss.
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.
Measuring Re-identification Risk
In this work, we present a new theoretical framework to measure re-identification risk in such user representations.
Structured Dynamic Pricing: Optimal Regret in a Global Shrinkage Model
We consider dynamic pricing strategies in a streamed longitudinal data set-up where the objective is to maximize, over time, the cumulative profit across a large number of customer segments.
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.
Prediction Sets for High-Dimensional Mixture of Experts Models
Large datasets make it possible to build predictive models that can capture heterogenous relationships between the response variable and features.
GRASP: A Goodness-of-Fit Test for Classification Learning
Performance of classifiers is often measured in terms of average accuracy on test data.
The curse of overparametrization in adversarial training: Precise analysis of robust generalization for random features regression
Our developed theory reveals the nontrivial effect of overparametrization on robustness and indicates that for adversarially trained random features models, high overparametrization can hurt robust generalization.
Adversarial robustness for latent models: Revisiting the robust-standard accuracies tradeoff
We develop a theory to show that the low-dimensional manifold structure allows one to obtain models that are nearly optimal with respect to both, the standard accuracy and the robust accuracy measures.
Controlling the False Split Rate in Tree-Based Aggregation
In many domains, data measurements can naturally be associated with the leaves of a tree, expressing the relationships among these measurements.
Fundamental Tradeoffs in Distributionally Adversarial Training
We study the tradeoff between standard risk and adversarial risk and derive the Pareto-optimal tradeoff, achievable over specific classes of models, in the infinite data limit with features dimension kept fixed.
Near-Optimal Procedures for Model Discrimination with Non-Disclosure Properties
Here we provide matching upper and lower bounds on the sample complexity as given by $\min\{1/\Delta^2,\sqrt{r}/\Delta\}$ up to a constant factor; here $\Delta$ is a measure of separation between $\mathbb{P}_0$ and $\mathbb{P}_1$ and $r$ is the rank of the design covariance matrix.
Precise Statistical Analysis of Classification Accuracies for Adversarial Training
Despite the wide empirical success of modern machine learning algorithms and models in a multitude of applications, they are known to be highly susceptible to seemingly small indiscernible perturbations to the input data known as \emph{adversarial attacks}.
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.
Precise Tradeoffs in Adversarial Training for Linear Regression
Furthermore, we precisely characterize the standard/robust accuracy and the corresponding tradeoff achieved by a contemporary mini-max adversarial training approach in a high-dimensional regime where the number of data points and the parameters of the model grow in proportion to each other.
Online Debiasing for Adaptively Collected High-dimensional Data with Applications to Time Series Analysis
Adaptive collection of data is commonplace in applications throughout science and engineering.
New Computational and Statistical Aspects of Regularized Regression with Application to Rare Feature Selection and Aggregation
Prior knowledge on properties of a target model often come as discrete or combinatorial descriptions.
Analysis of a Two-Layer Neural Network via Displacement Convexity
We prove that, in the limit in which the number of neurons diverges, the evolution of gradient descent converges to a Wasserstein gradient flow in the space of probability distributions over $\Omega$.
Multi-Product Dynamic Pricing in High-Dimensions with Heterogeneous Price Sensitivity
We measure the performance of a pricing policy in terms of regret, which is the expected revenue loss with respect to a clairvoyant policy that knows the parameters of the choice model in advance and always sets the revenue-maximizing prices.
Perturbation Bounds for Procrustes, Classical Scaling, and Trilateration, with Applications to Manifold Learning
One of the common tasks in unsupervised learning is dimensionality reduction, where the goal is to find meaningful low-dimensional structures hidden in high-dimensional data.
False Discovery Rate Control via Debiased Lasso
We consider the problem of variable selection in high-dimensional statistical models where the goal is to report a set of variables, out of many predictors $X_1, \dotsc, X_p$, that are relevant to a response of interest.
Theoretical insights into the optimization landscape of over-parameterized shallow neural networks
In this paper we study the problem of learning a shallow artificial neural network that best fits a training data set.
A Flexible Framework for Hypothesis Testing in High-dimensions
By duality between hypotheses testing and confidence intervals, the proposed framework can be used to obtain valid confidence intervals for various functionals of the model parameters.
Perishability of Data: Dynamic Pricing under Varying-Coefficient Models
In the first one, feature vectors are chosen antagonistically by nature and we prove that the regret of PSGD pricing policy is of order $O(\sqrt{T} + \sum_{t=1}^T \sqrt{t}\delta_t)$.
Dynamic Pricing in High-dimensions
We study the pricing problem faced by a firm that sells a large number of products, described via a wide range of features, to customers that arrive over time.
Performance of a community detection algorithm based on semidefinite programming
In this paper we study in detail several practical aspects of this new algorithm based on semidefinite programming for the detection of the planted partition.
Online Rules for Control of False Discovery Rate and False Discovery Exceedance
In this paper we consider the problem of controlling FDR in an "online manner".
De-biasing the Lasso: Optimal Sample Size for Gaussian Designs
When the covariance is known, we prove that the debiased estimator is asymptotically Gaussian under the nearly optimal condition $s_0 = o(n/ (\log p)^2)$.
1-Bit Matrix Completion under Exact Low-Rank Constraint
We consider the problem of noisy 1-bit matrix completion under an exact rank constraint on the true underlying matrix $M^*$.
On Online Control of False Discovery Rate
Given a sequence of null hypotheses $\mathcal{H}(n) = (H_1,..., H_n)$, Benjamini and Hochberg \cite{benjamini1995controlling} introduced the false discovery rate (FDR) criterion, which is the expected proportion of false positives among rejected null hypotheses, and proposed a testing procedure that controls FDR below a pre-assigned significance level.
Confidence Intervals and Hypothesis Testing for High-Dimensional Statistical Models
This in turn implies that it is extremely challenging to quantify the `uncertainty' associated with a certain parameter estimate.
Nearly Optimal Sample Size in Hypothesis Testing for High-Dimensional Regression
In the regime where the number of parameters $p$ is comparable to or exceeds the sample size $n$, a successful approach uses an $\ell_1$-penalized least squares estimator, known as Lasso.
Confidence Intervals and Hypothesis Testing for High-Dimensional Regression
This in turn implies that it is extremely challenging to quantify the \emph{uncertainty} associated with a certain parameter estimate.
Model Selection for High-Dimensional Regression under the Generalized Irrepresentability Condition
In the high-dimensional regression model a response variable is linearly related to $p$ covariates, but the sample size $n$ is smaller than $p$.
Efficient Reinforcement Learning for High Dimensional Linear Quadratic Systems
In particular, our algorithm has an average cost of $(1+\eps)$ times the optimum cost after $T = \polylog(p) O(1/\eps^2)$.
Hypothesis Testing in High-Dimensional Regression under the Gaussian Random Design Model: Asymptotic Theory
In this case we prove that a similar distributional characterization (termed `standard distributional limit') holds for $n$ much larger than $s_0(\log p)^2$.
Learning Topic Models and Latent Bayesian Networks Under Expansion Constraints
The sufficient conditions for identifiability of these models are primarily based on weak expansion constraints on the topic-word matrix, for topic models, and on the directed acyclic graph, for Bayesian networks.
