Search Results for author:
Found 28 papers, 14 papers with code
NTIRE 2020 Challenge on Real-World Image Super-Resolution: Methods and Results
This paper reviews the NTIRE 2020 challenge on real world super-resolution.
BlackJAX: Composable Bayesian inference in JAX
BlackJAX is a library implementing sampling and variational inference algorithms commonly used in Bayesian computation.
Faceptor: A Generalist Model for Face Perception
This design enhances the unification of model structure while improving application efficiency in terms of storage overhead.
DeepLight: Deep Lightweight Feature Interactions for Accelerating CTR Predictions in Ad Serving
To address the issue of significantly increased serving delay and high memory usage for ad serving in production, this paper presents \emph{DeepLight}: a framework to accelerate the CTR predictions in three aspects: 1) accelerate the model inference via explicitly searching informative feature interactions in the shallow component; 2) prune redundant layers and parameters at intra-layer and inter-layer level in the DNN component; 3) promote the sparsity of the embedding layer to preserve the most discriminant signals.
Ranked #7 on
Click-Through Rate Prediction
on Avazu
Adversarial Attacks against Windows PE Malware Detection: A Survey of the State-of-the-Art
Then, we conduct a comprehensive and systematic review to categorize the state-of-the-art adversarial attacks against PE malware detection, as well as corresponding defenses to increase the robustness of Windows PE malware detection.
A Contour Stochastic Gradient Langevin Dynamics Algorithm for Simulations of Multi-modal Distributions
We propose an adaptively weighted stochastic gradient Langevin dynamics algorithm (SGLD), so-called contour stochastic gradient Langevin dynamics (CSGLD), for Bayesian learning in big data statistics.
Non-convex Learning via Replica Exchange Stochastic Gradient MCMC
Replica exchange Monte Carlo (reMC), also known as parallel tempering, is an important technique for accelerating the convergence of the conventional Markov Chain Monte Carlo (MCMC) algorithms.
Ranked #77 on
Image Classification
on CIFAR-100
(using extra training data)
Provably Convergent Schrödinger Bridge with Applications to Probabilistic Time Series Imputation
We show that optimizing the transport cost improves the performance and the proposed algorithm achieves the state-of-the-art result in healthcare and environmental data while exhibiting the advantage of exploring both temporal and feature patterns in probabilistic time series imputation.
An Adaptive Empirical Bayesian Method for Sparse Deep Learning
We propose a novel adaptive empirical Bayesian method for sparse deep learning, where the sparsity is ensured via a class of self-adaptive spike-and-slab priors.
Accelerating Convergence of Replica Exchange Stochastic Gradient MCMC via Variance Reduction
Replica exchange stochastic gradient Langevin dynamics (reSGLD) has shown promise in accelerating the convergence in non-convex learning; however, an excessively large correction for avoiding biases from noisy energy estimators has limited the potential of the acceleration.
Interacting Contour Stochastic Gradient Langevin Dynamics
We propose an interacting contour stochastic gradient Langevin dynamics (ICSGLD) sampler, an embarrassingly parallel multiple-chain contour stochastic gradient Langevin dynamics (CSGLD) sampler with efficient interactions.
Toward Real World Stereo Image Super-Resolution via Hybrid Degradation Model and Discriminator for Implied Stereo Image Information
Real-world stereo image super-resolution has a significant influence on enhancing the performance of computer vision systems.
Can multiple-choice questions really be useful in detecting the abilities of LLMs?
Additionally, we propose two methods to quantify the consistency and confidence of LLMs' output, which can be generalized to other QA evaluation benchmarks.
Accelerating Approximate Thompson Sampling with Underdamped Langevin Monte Carlo
Approximate Thompson sampling with Langevin Monte Carlo broadens its reach from Gaussian posterior sampling to encompass more general smooth posteriors.
Using Deep Neural Networks to Automate Large Scale Statistical Analysis for Big Data Applications
We propose to use deep neural networks to automate the SA process.
Adaptive low rank and sparse decomposition of video using compressive sensing
We address the problem of reconstructing and analyzing surveillance videos using compressive sensing.
Bayesian Deep Learning via Stochastic Gradient MCMC with a Stochastic Approximation Adaptation
We propose a robust Bayesian deep learning algorithm to infer complex posteriors with latent variables.
Bayesian Sparse learning with preconditioned stochastic gradient MCMC and its applications
The algorithm utilizes a set of spike-and-slab priors for the parameters in the deep neural network.
An adaptive Hessian approximated stochastic gradient MCMC method
The bias introduced by stochastic approximation is controllable and can be analyzed theoretically.
Information Directed Sampling for Sparse Linear Bandits
Stochastic sparse linear bandits offer a practical model for high-dimensional online decision-making problems and have a rich information-regret structure.
Non-reversible Parallel Tempering for Uncertainty Approximation in Deep Learning
Parallel tempering (PT), also known as replica exchange, is the go-to workhorse for simulations of multi-modal distributions.
On Convergence of Federated Averaging Langevin Dynamics
We develop theoretical guarantees for FA-LD for strongly log-concave distributions with non-i. i. d data and study how the injected noise and the stochastic-gradient noise, the heterogeneity of data, and the varying learning rates affect the convergence.
Non-reversible Parallel Tempering for Deep Posterior Approximation
Notably, in big data scenarios, we obtain an appealing communication cost $O(P\log P)$ based on the optimal window size.
Non-convex Bayesian Learning via Stochastic Gradient Markov Chain Monte Carlo
We also present the population-chain replica exchange based on non-reversibility and obtain an optimal round-trip rate for deep learning.
Short-Term Multi-Horizon Line Loss Rate Forecasting of a Distribution Network Using Attention-GCN-LSTM
Accurately predicting line loss rates is vital for effective line loss management in distribution networks, especially over short-term multi-horizons ranging from one hour to one week.
Reflected Schrödinger Bridge for Constrained Generative Modeling
Diffusion models have become the go-to method for large-scale generative models in real-world applications.
Widely Linear Matched Filter: A Lynchpin towards the Interpretability of Complex-valued CNNs
However, applying this paradigm to illuminate the interpretability of complex-valued CNNs meets a formidable obstacle: the extension of matched filtering to a general class of noncircular complex-valued data, referred to here as the widely linear matched filter (WLMF), has been only implicit in the literature.
NTIRE 2024 Challenge on Low Light Image Enhancement: Methods and Results
This paper reviews the NTIRE 2024 low light image enhancement challenge, highlighting the proposed solutions and results.
