no code implementations • 2 Feb 2024 • Sungee Hong, Zhengling Qi, Raymond K. W. Wong
We consider the problem of distributional off-policy evaluation which serves as the foundation of many distributional reinforcement learning (DRL) algorithms.
1 code implementation • 29 Jan 2023 • Jiangyuan Li, Thanh V. Nguyen, Chinmay Hegde, Raymond K. W. Wong
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.
no code implementations • 26 Jan 2022 • Zhenyu Wei, Raymond K. W. Wong, Thomas C. M. Lee
In the signal processing and statistics literature, the minimum description length (MDL) principle is a popular tool for choosing model complexity.
no code implementations • 10 Sep 2021 • Jiayi Wang, Zhengling Qi, Raymond K. W. Wong
Offline policy evaluation (OPE) is considered a fundamental and challenging problem in reinforcement learning (RL).
1 code implementation • NeurIPS 2021 • Jiangyuan Li, Thanh V. Nguyen, Chinmay Hegde, Raymond K. W. Wong
In this paper, we study the implicit bias of gradient descent for sparse regression.
no code implementations • 9 Jun 2021 • Jiayi Wang, Raymond K. W. Wong, Xiaojun Mao, Kwun Chuen Gary Chan
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).
no code implementations • 22 Oct 2020 • Ya Zhou, Raymond K. W. Wong, Kejun He
In this article, we provide useful results of CP degeneracy in tensor regression problems.
no code implementations • ICML 2020 • Weidong Liu, Xiaojun Mao, Raymond K. W. Wong
In this paper, we consider matrix completion with absolute deviation loss and obtain an estimator of the median matrix.
no code implementations • 27 Nov 2019 • Thanh V. Nguyen, Raymond K. W. Wong, Chinmay Hegde
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.
no code implementations • 19 Dec 2018 • Xiaojun Mao, Raymond K. W. Wong, Song Xi Chen
Although missing structure is a key component to any missing data problems, existing matrix completion methods often assume a simple uniform missing mechanism.
no code implementations • 2 Jun 2018 • Thanh V. Nguyen, Raymond K. W. Wong, Chinmay Hegde
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.
1 code implementation • 9 Nov 2017 • Thanh V. Nguyen, Raymond K. W. Wong, Chinmay Hegde
To our knowledge, our work introduces the first computationally efficient algorithm for double-sparse coding that enjoys rigorous statistical guarantees.
1 code implementation • 28 Aug 2015 • Raymond K. W. Wong, Vinay L. Kashyap, Thomas C. M. Lee, David A. van Dyk
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
no code implementations • 1 Mar 2015 • Raymond K. W. Wong, Thomas C. M. Lee
This paper considers the problem of matrix completion when the observed entries are noisy and contain outliers.