Search Results for author:
Found 29 papers, 3 papers with code
Distribution-Free Rates in Neyman-Pearson Classification
We consider the problem of Neyman-Pearson classification which models unbalanced classification settings where error w. r. t.
Efficient Estimation of the Central Mean Subspace via Smoothed Gradient Outer Products
We consider the problem of sufficient dimension reduction (SDR) for multi-index models.
Tight Rates in Supervised Outlier Transfer Learning
A critical barrier to learning an accurate decision rule for outlier detection is the scarcity of outlier data.
Nonlinear Meta-Learning Can Guarantee Faster Rates
Many recent theoretical works on \emph{meta-learning} aim to achieve guarantees in leveraging similar representational structures from related tasks towards simplifying a target task.
Classification Tree Pruning Under Covariate Shift
We consider the problem of \emph{pruning} a classification tree, that is, selecting a suitable subtree that balances bias and variance, in common situations with inhomogeneous training data.
Limits of Model Selection under Transfer Learning
Theoretical studies on transfer learning or domain adaptation have so far focused on situations with a known hypothesis class or model; however in practice, some amount of model selection is usually involved, often appearing under the umbrella term of hyperparameter-tuning: for example, one may think of the problem of tuning for the right neural network architecture towards a target task, while leveraging data from a related source task.
Tracking Most Significant Arm Switches in Bandits
In bandit with distribution shifts, one aims to automatically adapt to unknown changes in reward distribution, and restart exploration when necessary.
Nuances in Margin Conditions Determine Gains in Active Learning
We consider nonparametric classification with smooth regression functions, where it is well known that notions of margin in $E[Y|X]$ determine fast or slow rates in both active and passive learning.
An Efficient One-Class SVM for Anomaly Detection in the Internet of Things
Insecure Internet of things (IoT) devices pose significant threats to critical infrastructure and the Internet at large; detecting anomalous behavior from these devices remains of critical importance, but fast, efficient, accurate anomaly detection (also called "novelty detection") for these classes of devices remains elusive.
Feature Extraction for Novelty Detection in Network Traffic
To facilitate such exploration, we develop a systematic framework, open-source toolkit, and public Python library that makes it both possible and easy to extract and generate features from network traffic and perform and end-to-end evaluation of these representations across most prevalent modern novelty detection models.
A No-Free-Lunch Theorem for MultiTask Learning
A perplexing fact remains in the evolving theory on the subject: while we would hope for performance bounds that account for the contribution from multiple tasks, the vast majority of analyses result in bounds that improve at best in the number $n$ of samples per task, but most often do not improve in $N$.
On the Value of Target Data in Transfer Learning
We aim to understand the value of additional labeled or unlabeled target data in transfer learning, for any given amount of source data; this is motivated by practical questions around minimizing sampling costs, whereby, target data is usually harder or costlier to acquire than source data, but can yield better accuracy.
Gaussian Sketching yields a J-L Lemma in RKHS
The main contribution of the paper is to show that Gaussian sketching of a kernel-Gram matrix $\boldsymbol K$ yields an operator whose counterpart in an RKHS $\mathcal H$, is a \emph{random projection} operator---in the spirit of Johnson-Lindenstrauss (J-L) lemma.
PAC-Bayes Tree: weighted subtrees with guarantees
We present a weighted-majority classification approach over subtrees of a fixed tree, which provably achieves excess-risk of the same order as the best tree-pruning.
Quickshift++: Provably Good Initializations for Sample-Based Mean Shift
We provide initial seedings to the Quick Shift clustering algorithm, which approximate the locally high-density regions of the data.
Marginal Singularity, and the Benefits of Labels in Covariate-Shift
We present new minimax results that concisely capture the relative benefits of source and target labeled data, under covariate-shift.
Achieving the time of $1$-NN, but the accuracy of $k$-NN
The approach consists of aggregating denoised $1$-NN predictors over a small number of distributed subsamples.
An Adaptive Strategy for Active Learning with Smooth Decision Boundary
The problem of adaptivity (to unknown distributional parameters) has remained opened since the seminal work of Castro and Nowak (2007), which first established (active learning) rates for this setting.
Adaptivity to Noise Parameters in Nonparametric Active Learning
This work addresses various open questions in the theory of active learning for nonparametric classification.
Modal-set estimation with an application to clustering
We present a first procedure that can estimate -- with statistical consistency guarantees -- any local-maxima of a density, under benign distributional conditions.
Optimal rates for k-NN density and mode estimation
We present two related contributions of independent interest: (1) high-probability finite sample rates for $k$-NN density estimation, and (2) practical mode estimators -- based on $k$-NN -- which attain minimax-optimal rates under surprisingly general distributional conditions.
Consistent procedures for cluster tree estimation and pruning
For a density $f$ on ${\mathbb R}^d$, a {\it high-density cluster} is any connected component of $\{x: f(x) \geq \lambda\}$, for some $\lambda > 0$.
Consistency of Causal Inference under the Additive Noise Model
We analyze a family of methods for statistical causal inference from sample under the so-called Additive Noise Model.
Regression-tree Tuning in a Streaming Setting
We consider the problem of maintaining the data-structures of a partition-based regression procedure in a setting where the training data arrives sequentially over time.
Adaptivity to Local Smoothness and Dimension in Kernel Regression
We present the first result for kernel regression where the procedure adapts locally at a point $x$ to both the unknown local dimension of the metric and the unknown H\{o}lder-continuity of the regression function at $x$.
Gradient Weights help Nonparametric Regressors
In regression problems over $\real^d$, the unknown function $f$ often varies more in some coordinates than in others.
k-NN Regression Adapts to Local Intrinsic Dimension
Many nonparametric regressors were recently shown to converge at rates that depend only on the intrinsic dimension of data.
Fast, smooth and adaptive regression in metric spaces
It was recently shown that certain nonparametric regressors can escape the curse of dimensionality in the sense that their convergence rates adapt to the intrinsic dimension of data (\cite{BL:65, SK:77}).
