Search Results for author:
Found 18 papers, 7 papers with code
Universal Lower Bounds and Optimal Rates: Achieving Minimax Clustering Error in Sub-Exponential Mixture Models
In such mixtures, we establish that Bregman hard clustering, a variant of Lloyd's algorithm employing a Bregman divergence, is rate optimal.
Differences Between Hard and Noisy-labeled Samples: An Empirical Study
We study various data partitioning methods in the presence of label noise and observe that filtering out noisy samples from hard samples with this proposed metric results in the best datasets as evidenced by the high test accuracy achieved after models are trained on the filtered datasets.
When Does Bottom-up Beat Top-down in Hierarchical Community Detection?
We also establish that this bottom-up algorithm attains the information-theoretic threshold for exact recovery at intermediate levels of the hierarchy.
Relaxing the Additivity Constraints in Decentralized No-Regret High-Dimensional Bayesian Optimization
Bayesian Optimization (BO) is typically used to optimize an unknown function $f$ that is noisy and costly to evaluate, by exploiting an acquisition function that must be maximized at each optimization step.
Leveraging Unlabeled Data to Track Memorization
We empirically show the effectiveness of our metric in tracking memorization on various architectures and datasets and provide theoretical insights into the design of the susceptibility metric.
Stochastic Second-Order Methods Improve Best-Known Sample Complexity of SGD for Gradient-Dominated Function
We prove that the total sample complexity of SCRN in achieving $\epsilon$-global optimum is $\mathcal{O}(\epsilon^{-7/(2\alpha)+1})$ for $1\le\alpha< 3/2$ and $\mathcal{\tilde{O}}(\epsilon^{-2/(\alpha)})$ for $3/2\le\alpha\le 2$.
Momentum-Based Policy Gradient with Second-Order Information
SHARP algorithm is parameter-free, achieving $\epsilon$-approximate first-order stationary point with $O(\epsilon^{-3})$ number of trajectories, while using a batch size of $O(1)$ at each iteration.
Disparity Between Batches as a Signal for Early Stopping
We propose a metric for evaluating the generalization ability of deep neural networks trained with mini-batch gradient descent.
Early Stopping by Gradient Disparity
Validation-based early-stopping methods are one of the most popular techniques used to avoid over-training deep neural networks.
Generalization Comparison of Deep Neural Networks via Output Sensitivity
We find a rather strong empirical relation between the output sensitivity and the variance in the bias-variance decomposition of the loss function, which hints on using sensitivity as a metric for comparing the generalization performance of networks, without requiring labeled data.
A User Study of Perceived Carbon Footprint
We propose a statistical model to understand people's perception of their carbon footprint.
Learning Hawkes Processes from a Handful of Events
It is also able to take into account the uncertainty in the model parameters by learning a posterior distribution over them.
On the Reflection of Sensitivity in the Generalization Error
We find a rather strong empirical relation between the output sensitivity and the variance in the bias-variance decomposition of the loss function, which hints on using sensitivity as a metric for comparing generalization performance of networks, without requiring labeled data.
Coordinate Descent with Bandit Sampling
Ideally, we would update the decision variable that yields the largest decrease in the cost function.
Stochastic Optimization with Bandit Sampling
This approach for sampling datapoints is general, and can be used in conjunction with any algorithm that uses an unbiased gradient estimation -- we expect it to have broad applicability beyond the specific examples explored in this work.
Dictionary Learning Based on Sparse Distribution Tomography
We propose a new statistical dictionary learning algorithm for sparse signals that is based on an $\alpha$-stable innovation model.
Where You Are Is Who You Are: User Identification by Matching Statistics
The accuracy obtained under this optimal method can thus be used to quantify the maximum level of user identification that is possible in such settings.
The Entropy of Conditional Markov Trajectories
To quantify the randomness of Markov trajectories with fixed initial and final states, Ekroot and Cover proposed a closed-form expression for the entropy of trajectories of an irreducible finite state Markov chain.
Information Theory Information Theory Applications
