Zobrazeno 1 - 10
of 183
pro vyhledávání: '"Truong, Lan"'
Autor:
Truong, Lan V.
In this paper, we introduce various covering number bounds for linear function classes, each subject to different constraints on input and matrix norms. These bounds are contingent on the rank of each class of matrices. We then apply these bounds to
Externí odkaz:
http://arxiv.org/abs/2410.11500
Autor:
Truong, Lan V.
Subset weighted-Tempered Gibbs Sampler (wTGS) has been recently introduced by Jankowiak to reduce the computation complexity per MCMC iteration in high-dimensional applications where the exact calculation of the posterior inclusion probabilities (PIP
Externí odkaz:
http://arxiv.org/abs/2304.02899
Autor:
Truong, Lan V.
In a recent paper, Ling et al. investigated the over-parametrized Deep Equilibrium Model (DEQ) with ReLU activation. They proved that the gradient descent converges to a globally optimal solution for the quadratic loss function at a linear convergenc
Externí odkaz:
http://arxiv.org/abs/2302.05797
We find the exact typical error exponent of constant composition generalized random Gilbert-Varshamov (RGV) codes over DMCs channels with generalized likelihood decoding. We show that the typical error exponent of the RGV ensemble is equal to the exp
Externí odkaz:
http://arxiv.org/abs/2211.12238
Autor:
Truong, Lan V.
A generative adversarial network (GAN) is a class of machine learning frameworks designed by Goodfellow et al. in 2014. In the GAN framework, the generative model is pitted against an adversary: a discriminative model that learns to determine whether
Externí odkaz:
http://arxiv.org/abs/2210.06005
Autor:
Truong, Lan V.
We show that the Rademacher complexity-based approach can generate non-vacuous generalisation bounds on Convolutional Neural Networks (CNNs) for classifying a small number of classes of images. The development of new Talagrand's contraction lemmas fo
Externí odkaz:
http://arxiv.org/abs/2208.04284
Autor:
Truong, Lan V.
This paper presents novel generalization bounds for the multi-kernel learning problem. Motivated by applications in sensor networks and spatial-temporal models, we assume that the dataset is mixed where each sample is taken from a finite pool of Mark
Externí odkaz:
http://arxiv.org/abs/2205.07313
This paper studies the concentration properties of random codes. Specifically, we show that, for discrete memoryless channels, the error exponent of a randomly generated code with pairwise-independent codewords converges in probability to its expecta
Externí odkaz:
http://arxiv.org/abs/2203.07853
Autor:
Truong, Lan V.
In this paper, we derive upper bounds on generalization errors for deep neural networks with Markov datasets. These bounds are developed based on Koltchinskii and Panchenko's approach for bounding the generalization error of combined classifiers with
Externí odkaz:
http://arxiv.org/abs/2201.11059
Autor:
Truong, Lan V.
We establish exact asymptotic expressions for the normalized mutual information and minimum mean-square-error (MMSE) of sparse linear regression in the sub-linear sparsity regime. Our result is achieved by a generalization of the adaptive interpolati
Externí odkaz:
http://arxiv.org/abs/2101.11156