Search Results for author:
Found 14 papers, 4 papers with code
Distributional Off-policy Evaluation with Bellman Residual Minimization
We consider the problem of distributional off-policy evaluation which serves as the foundation of many distributional reinforcement learning (DRL) algorithms.
Implicit Regularization for Group Sparsity
We study the implicit regularization of gradient descent towards structured sparsity via a novel neural reparameterization, which we call a diagonally grouped linear neural network.
Extending the Use of MDL for High-Dimensional Problems: Variable Selection, Robust Fitting, and Additive Modeling
In the signal processing and statistics literature, the minimum description length (MDL) principle is a popular tool for choosing model complexity.
Projected State-action Balancing Weights for Offline Reinforcement Learning
Offline policy evaluation (OPE) is considered a fundamental and challenging problem in reinforcement learning (RL).
Implicit Sparse Regularization: The Impact of Depth and Early Stopping
In this paper, we study the implicit bias of gradient descent for sparse regression.
Matrix Completion with Model-free Weighting
In particular, the proposed method achieves a stronger guarantee than existing work in terms of the scaling with respect to the observation probabilities, under asymptotically heterogeneous missing settings (where entry-wise observation probabilities can be of different orders).
CP Degeneracy in Tensor Regression
In this article, we provide useful results of CP degeneracy in tensor regression problems.
Median Matrix Completion: from Embarrassment to Optimality
In this paper, we consider matrix completion with absolute deviation loss and obtain an estimator of the median matrix.
Benefits of Jointly Training Autoencoders: An Improved Neural Tangent Kernel Analysis
Starting from a randomly initialized autoencoder network, we rigorously prove the linear convergence of gradient descent in two learning regimes, namely: (i) the weakly-trained regime where only the encoder is trained, and (ii) the jointly-trained regime where both the encoder and the decoder are trained.
Matrix Completion under Low-Rank Missing Mechanism
Although missing structure is a key component to any missing data problems, existing matrix completion methods often assume a simple uniform missing mechanism.
Autoencoders Learn Generative Linear Models
For each of these models, we prove that under suitable choices of hyperparameters, architectures, and initialization, autoencoders learned by gradient descent can successfully recover the parameters of the corresponding model.
Provably Accurate Double-Sparse Coding
To our knowledge, our work introduces the first computationally efficient algorithm for double-sparse coding that enjoys rigorous statistical guarantees.
Detecting Abrupt Changes in the Spectra of High-Energy Astrophysical Sources
We embed change points into a marked Poisson process, where photon wavelengths are regarded as marks and both the Poisson intensity parameter and the distribution of the marks are allowed to change.
Applications Instrumentation and Methods for Astrophysics
Matrix Completion with Noisy Entries and Outliers
This paper considers the problem of matrix completion when the observed entries are noisy and contain outliers.
