661 citations · 1.6k across the 30 of their papers we have counts for
31 papers
Computationally-Efficient Neural Image Compression with Shallow Decoders
Yibo Yang, Stephan Mandt
Neural image compression methods have seen increasingly strong performance in recent years. However, they suffer orders of magnitude higher computational complexity compared to tra…
Neural Collapse Inspired Federated Learning with Non-iid Data
Chenxi Huang, Liang Xie, Yibo Yang +3
One of the challenges in federated learning is the non-independent and identically distributed (non-iid) characteristics between heterogeneous devices, which cause significant diff…
Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class Incremental Learning
Yibo Yang, Haobo Yuan, Xiangtai Li +3
Few-shot class-incremental learning (FSCIL) has been a challenging problem as only a few training samples are accessible for each novel class in the new sessions. Finetuning the ba…
Unpolarized Transverse-Momentum-Dependent Parton Distributions of the Nucleon from Lattice QCD
Lattice Parton Collaboration, Jin-Chen He, Min-Huan Chu +8
We present a first lattice QCD calculation of the unpolarized nucleon's isovector transverse-momentum-dependent parton distribution functions (TMDPDFs), which are essential to pred…
Towards Theoretically Inspired Neural Initialization Optimization
Yibo Yang, Hong Wang, Haobo Yuan +1
Automated machine learning has been widely explored to reduce human efforts in designing neural architectures and looking for proper hyperparameters. In the domain of neural initia…
Muon g-2 with overlap valence fermions
Gen Wang, Terrence Draper, Keh-Fei Liu +1
We present a lattice calculation of the leading order (LO) hadronic vacuum polarization (HVP) contribution to the muon anomalous magnetic moment for the connected light and strange…
Scalable Uncertainty Quantification for Deep Operator Networks using Randomized Priors
Yibo Yang, Georgios Kissas, Paris Perdikaris
We present a simple and effective approach for posterior uncertainty quantification in deep operator networks (DeepONets); an emerging paradigm for supervised learning in function…
Insights from Generative Modeling for Neural Video Compression
Ruihan Yang, Yibo Yang, Joseph Marino +1
While recent machine learning research has revealed connections between deep generative models such as VAEs and rate-distortion losses used in learned compression, most of this wor…
Output-Weighted Sampling for Multi-Armed Bandits with Extreme Payoffs
Yibo Yang, Antoine Blanchard, Themistoklis Sapsis +1
We present a new type of acquisition functions for online decision making in multi-armed and contextual bandit problems with extreme payoffs. Specifically, we model the payoff func…
Towards Improving the Consistency, Efficiency, and Flexibility of Differentiable Neural Architecture Search
Yibo Yang, Shan You, Hongyang Li +3
Most differentiable neural architecture search methods construct a super-net for search and derive a target-net as its sub-graph for evaluation. There exists a significant gap betw…
Stretchable Cells Help DARTS Search Better
Tao Huang, Shan You, Yibo Yang +4
Differentiable neural architecture search (DARTS) has gained much success in discovering flexible and diverse cell types. To reduce the evaluation gap, the supernet is expected to…
ISTA-NAS: Efficient and Consistent Neural Architecture Search by Sparse Coding
Yibo Yang, Hongyang Li, Shan You +3
Neural architecture search (NAS) aims to produce the optimal sparse solution from a high-dimensional space spanned by all candidate connections. Current gradient-based NAS methods…
Hierarchical Autoregressive Modeling for Neural Video Compression
Ruihan Yang, Yibo Yang, Joseph Marino +1
Recent work by Marino et al. (2020) showed improved performance in sequential density estimation by combining masked autoregressive flows with hierarchical latent variable models.…
Improving Inference for Neural Image Compression
Yibo Yang, Robert Bamler, Stephan Mandt
We consider the problem of lossy image compression with deep latent variable models. State-of-the-art methods build on hierarchical variational autoencoders (VAEs) and learn infere…
Bayesian differential programming for robust systems identification under uncertainty
Yibo Yang, Mohamed Aziz Bhouri, Paris Perdikaris
This paper presents a machine learning framework for Bayesian systems identification from noisy, sparse and irregular observations of nonlinear dynamical systems. The proposed meth…
Spatial Pyramid Based Graph Reasoning for Semantic Segmentation
Xia Li, Yibo Yang, Qijie Zhao +3
The convolution operation suffers from a limited receptive filed, while global modeling is fundamental to dense prediction tasks, such as semantic segmentation. In this paper, we a…
Exact artificial boundary conditions of 1D semi-discretized peridynamics
Songsong Ji, Gang Pang, Jiwei Zhang +2
The peridynamic theory reformulates the equations of continuum mechanics in terms of integro-differential equations instead of partial differential equations. It is not trivial to…
Variational Bayesian Quantization
Yibo Yang, Robert Bamler, Stephan Mandt
We propose a novel algorithm for quantizing continuous latent representations in trained models. Our approach applies to deep probabilistic models, such as variational autoencoders…
Dynamical System Inspired Adaptive Time Stepping Controller for Residual Network Families
Yibo Yang, Jianlong Wu, Hongyang Li +3
The correspondence between residual networks and dynamical systems motivates researchers to unravel the physics of ResNets with well-developed tools in numeral methods of ODE syste…
SOGNet: Scene Overlap Graph Network for Panoptic Segmentation
Yibo Yang, Hongyang Li, Xia Li +3
The panoptic segmentation task requires a unified result from semantic and instance segmentation outputs that may contain overlaps. However, current studies widely ignore modeling…
Expectation-Maximization Attention Networks for Semantic Segmentation
Xia Li, Zhisheng Zhong, Jianlong Wu +3
Self-attention mechanism has been widely used for various tasks. It is designed to compute the representation of each position by a weighted sum of the features at all positions. T…
Machine learning in cardiovascular flows modeling: Predicting arterial blood pressure from non-invasive 4D flow MRI data using physics-informed neural networks
Georgios Kissas, Yibo Yang, Eileen Hwuang +3
Advances in computational science offer a principled pipeline for predictive modeling of cardiovascular flows and aspire to provide a valuable tool for monitoring, diagnostics and…
Conditional deep surrogate models for stochastic, high-dimensional, and multi-fidelity systems
Yibo Yang, Paris Perdikaris
We present a probabilistic deep learning methodology that enables the construction of predictive data-driven surrogates for stochastic systems. Leveraging recent advances in variat…
Physics-informed deep generative models
Yibo Yang, Paris Perdikaris
We consider the application of deep generative models in propagating uncertainty through complex physical systems. Specifically, we put forth an implicit variational inference form…