Search Results for author:
Found 18 papers, 0 papers with code
Collaborative Learning with Different Labeling Functions
We study a variant of Collaborative PAC Learning, in which we aim to learn an accurate classifier for each of the $n$ data distributions, while minimizing the number of samples drawn from them in total.
On the Distance from Calibration in Sequential Prediction
We then show that an $O(\sqrt{T})$ lower calibration distance can be achieved via a simple minimax argument and a reduction to online learning on a Lipschitz class.
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.
A Fourier Approach to Mixture Learning
Regev and Vijayaraghavan (2017) showed that with $\Delta = \Omega(\sqrt{\log k})$ separation, the means can be learned using $\mathrm{poly}(k, d)$ samples, whereas super-polynomially many samples are required if $\Delta = o(\sqrt{\log k})$ and $d = \Omega(\log k)$.
Open Problem: Properly learning decision trees in polynomial time?
The previous fastest algorithm for this problem ran in $n^{O(\log n)}$ time, a consequence of Ehrenfeucht and Haussler (1989)'s classic algorithm for the distribution-free setting.
Properly learning decision trees in almost polynomial time
We give an $n^{O(\log\log n)}$-time membership query algorithm for properly and agnostically learning decision trees under the uniform distribution over $\{\pm 1\}^n$.
Decision tree heuristics can fail, even in the smoothed setting
Greedy decision tree learning heuristics are mainstays of machine learning practice, but theoretical justification for their empirical success remains elusive.
Exponential Weights Algorithms for Selective Learning
We study the selective learning problem introduced by Qiao and Valiant (2019), in which the learner observes $n$ labeled data points one at a time.
Stronger Calibration Lower Bounds via Sidestepping
In this paper, we prove an $\Omega(T^{0. 528})$ bound on the calibration error, which is the first super-$\sqrt{T}$ lower bound for this setting to the best of our knowledge.
A Theory of Selective Prediction
The algorithm is allowed to choose when to make the prediction as well as the length of the prediction window, possibly depending on the observations so far.
On Generalization Error Bounds of Noisy Gradient Methods for Non-Convex Learning
We develop a new framework, termed Bayes-Stability, for proving algorithm-dependent generalization error bounds.
Do Outliers Ruin Collaboration?
We consider the problem of learning a binary classifier from $n$ different data sources, among which at most an $\eta$ fraction are adversarial.
Collaborative PAC Learning
We introduce a collaborative PAC learning model, in which k players attempt to learn the same underlying concept.
Learning Discrete Distributions from Untrusted Batches
Specifically, we consider the setting where there is some underlying distribution, $p$, and each data source provides a batch of $\ge k$ samples, with the guarantee that at least a $(1-\epsilon)$ fraction of the sources draw their samples from a distribution with total variation distance at most $\eta$ from $p$.
Nearly Optimal Sampling Algorithms for Combinatorial Pure Exploration
We provide a novel instance-wise lower bound for the sample complexity of the problem, as well as a nontrivial sampling algorithm, matching the lower bound up to a factor of $\ln|\mathcal{F}|$.
Practical Algorithms for Best-K Identification in Multi-Armed Bandits
In the Best-$K$ identification problem (Best-$K$-Arm), we are given $N$ stochastic bandit arms with unknown reward distributions.
Nearly Instance Optimal Sample Complexity Bounds for Top-k Arm Selection
In the Best-$k$-Arm problem, we are given $n$ stochastic bandit arms, each associated with an unknown reward distribution.
Towards Instance Optimal Bounds for Best Arm Identification
$H(I)=\sum_{i=2}^n\Delta_{[i]}^{-2}$ is the complexity of the instance.
