Search Results for author:
Found 28 papers, 4 papers with code
Insufficient Statistics Perturbation: Stable Estimators for Private Least Squares
We present a sample- and time-efficient differentially private algorithm for ordinary least squares, with error that depends linearly on the dimension and is independent of the condition number of $X^\top X$, where $X$ is the design matrix.
A Combinatorial Approach to Robust PCA
We study the problem of recovering Gaussian data under adversarial corruptions when the noises are low-rank and the corruptions are on the coordinate level.
Transformers can optimally learn regression mixture models
In this work, we investigate the hypothesis that transformers can learn an optimal predictor for mixtures of regressions.
A decoder-only foundation model for time-series forecasting
Motivated by recent advances in large language models for Natural Language Processing (NLP), we design a time-series foundation model for forecasting whose out-of-the-box zero-shot performance on a variety of public datasets comes close to the accuracy of state-of-the-art supervised forecasting models for each individual dataset.
Linear Regression using Heterogeneous Data Batches
A common approach assumes that the sources fall in one of several unknown subgroups, each with an unknown input distribution and input-output relationship.
Long-term Forecasting with TiDE: Time-series Dense Encoder
Recent work has shown that simple linear models can outperform several Transformer based approaches in long term time-series forecasting.
Ranked #3 on
Time Series Forecasting
on ETTh2 (192) Multivariate
Estimating Optimal Policy Value in General Linear Contextual Bandits
Whether this is possible for more realistic context distributions has remained an open and important question for tasks such as model selection.
Near Optimal Private and Robust Linear Regression
Under label-corruption, this is the first efficient linear regression algorithm to guarantee both $(\varepsilon,\delta)$-DP and robustness.
Efficient List-Decodable Regression using Batches
We begin the study of list-decodable linear regression using batches.
Trimmed Maximum Likelihood Estimation for Robust Learning in Generalized Linear Models
We study the problem of learning generalized linear models under adversarial corruptions.
DP-PCA: Statistically Optimal and Differentially Private PCA
For sub-Gaussian data, we provide nearly optimal statistical error rates even for $n=\tilde O(d)$.
Dirichlet Proportions Model for Hierarchically Coherent Probabilistic Forecasting
Probabilistic, hierarchically coherent forecasting is a key problem in many practical forecasting applications -- the goal is to obtain coherent probabilistic predictions for a large number of time series arranged in a pre-specified tree hierarchy.
Differential privacy and robust statistics in high dimensions
The key insight is that if we design an exponential mechanism that accesses the data only via one-dimensional robust statistics, then the resulting local sensitivity can be dramatically reduced.
Fisher-Pitman permutation tests based on nonparametric Poisson mixtures with application to single cell genomics
This paper investigates the theoretical and empirical performance of Fisher-Pitman-type permutation tests for assessing the equality of unknown Poisson mixture distributions.
SPECTRE: Defending Against Backdoor Attacks Using Robust Statistics
There have been promising attempts to use the intermediate representations of such a model to separate corrupted examples from clean ones.
Robust and Differentially Private Mean Estimation
In statistical learning and analysis from shared data, which is increasingly widely adopted in platforms such as federated learning and meta-learning, there are two major concerns: privacy and robustness.
Online Model Selection for Reinforcement Learning with Function Approximation
Towards this end, we consider the problem of model selection in RL with function approximation, given a set of candidate RL algorithms with known regret guarantees.
Robust Meta-learning for Mixed Linear Regression with Small Batches
Together, this approach is robust against outliers and achieves a graceful statistical trade-off; the lack of $\Omega(k^{1/2})$-size tasks can be compensated for with smaller tasks, which can now be as small as $O(\log k)$.
Meta-learning for mixed linear regression
In modern supervised learning, there are a large number of tasks, but many of them are associated with only a small amount of labeled data.
Sublinear Optimal Policy Value Estimation in Contextual Bandits
We study the problem of estimating the expected reward of the optimal policy in the stochastic disjoint linear bandit setting.
Optimal Estimation of Change in a Population of Parameters
Provided these paired observations, $\{(X_i, Y_i) \}_{i=1}^N$, our goal is to accurately estimate the \emph{distribution of the change in parameters}, $\delta_i := q_i - p_i$, over the population and properties of interest like the \emph{$\ell_1$-magnitude of the change} with sparse observations ($t\ll N$).
Maximum Likelihood Estimation for Learning Populations of Parameters
Precisely, for sufficiently large $N$, the MLE achieves the information theoretic optimal error bound of $\mathcal{O}(\frac{1}{t})$ for $t < c\log{N}$, with regards to the earth mover's distance (between the estimated and true distributions).
Efficient Algorithms and Lower Bounds for Robust Linear Regression
An error of $\Omega (\epsilon \sigma)$ is information-theoretically necessary, even with infinite sample size.
Estimating Learnability in the Sublinear Data Regime
In this setting, we show that with $O(\sqrt{d})$ samples, one can accurately estimate the fraction of the variance of the label that can be explained via the best linear function of the data.
Learning Populations of Parameters
Consider the following estimation problem: there are $n$ entities, each with an unknown parameter $p_i \in [0, 1]$, and we observe $n$ independent random variables, $X_1,\ldots, X_n$, with $X_i \sim $ Binomial$(t, p_i)$.
Recovering Structured Probability Matrices
When can accurate reconstruction be accomplished in the sparse data regime?
Spectrum Estimation from Samples
We consider this fundamental recovery problem in the regime where the number of samples is comparable, or even sublinear in the dimensionality of the distribution in question.
Isotropic Hashing
Most existing hashing methods adopt some projection functions to project the original data into several dimensions of real values, and then each of these projected dimensions is quantized into one bit (zero or one) by thresholding.
