arXiv research

DVE models dynamic changes in feature embeddings for better sequence-aware applications.

Noise-aware DP inference improves accuracy for complex models.

This work connects SAM to variational inference and evaluates its performance.

Proposes a new framework for uncertainty-aware LLM post-training.

TA-VAAL improves active learning by better utilizing task structures and overall data distribution.

Unified framework for fair regression in aware and unaware settings.

SVAT reduces investment risks by making stock models sensitive to adversarial perturbations.

Bayes-CATSI uses variational Bayesian deep learning for medical time series data imputation.

This paper establishes the asymptotic consistency of the {\it loss-calibrated variational Bayes} (LCVB) method. LCVB was proposed in~\cite{LaSiGh2011} as a method for approximately computing Bayesian posteriors in a `loss aware' manner. This methodology is also highly relevant in general data-driven decision-making con…

Paper develops a new RL method for MDPs with uncertainty, achieving better regret bounds.

Optimizes data acquisition in high-dimensional Bayesian optimization.

Bayesian neural networks improve uncertainty calibration without sacrificing accuracy.

We propose a novel visual context-aware filter generation module which incorporates contextual information present in images into Convolutional Neural Networks (CNNs). In contrast to traditional CNNs, we do not employ the same set of learned convolution filters for all input image instances. Our proposed input-conditio…

Improved DP-SGD for variational inference reduces noise and variance.

Bispectral OT improves dataset comparison by preserving intrinsic coherence.

Poisson variational autoencoders introduce a metabolic cost term that penalizes high baseline activity.

Proposes a model to generate 3D-aware images from 2D images.

New method calibrates predictions in chaotic systems using variational inference.

Quantum state preparation framework speeds up basket option pricing.

A simple approach to obtaining uncertainty-aware neural networks for regression is to do Bayesian linear regression (BLR) on the representation from the last hidden layer. Recent work [Riquelme et al., 2018, Azizzadenesheli et al., 2018] indicates that the method is promising, though it has been limited to homoscedasti…

Deep neural networks (DNNs) provide state-of-the-art results for a multitude of applications, but the approaches using DNNs for multimodal audiovisual applications do not consider predictive uncertainty associated with individual modalities. Bayesian deep learning methods provide principled confidence and quantify pred…

TALBO optimizes latent spaces for evolving design objectives.

MQTransformer improves forecast accuracy with context-aware attention.

STAR improves equivariant and invariant representation learning by routing projection heads.

Foundation for learning in changing conditions.

Nuclear segmentation in histology images is a challenging task due to significant variations in the shape and appearance of nuclei. One of the main hurdles in nuclear instance segmentation is overlapping nuclei where a smart algorithm is needed to separate each nucleus. In this paper, we introduce a proposal-free deep …

GAME improves matrix completion by considering subgroup-specific latent structures.

A neural network method tackles high-dimensional diffeomorphic mapping problems.

SIG model identifies invariant variables for MSDA with fewer domain constraints.

Donor-aware scRNA-seq benchmarks improve classification accuracy in inflammatory bowel disease.

Different types of Convolutional Neural Networks (CNNs) have been applied to detect cancerous lung nodules from computed tomography (CT) scans. However, the size of a nodule is very diverse and can range anywhere between 3 and 30 millimeters. The high variation of nodule sizes makes classifying them a difficult and cha…

KFT improves tensor forecasting by incorporating side information.

Deep learning has demonstrated success in health risk prediction especially for patients with chronic and progressing conditions. Most existing works focus on learning disease Network (StageNet) model to extract disease stage information from patient data and integrate it into risk prediction. StageNet is enabled by (1…

New method learns fair representations by separating out protected attributes.

SVGP KAN integrates uncertainty quantification into Kolmogorov-Arnold networks.

Structured Nonparametric Variational Inference for Dependent Latent Modeling

Proposes a geometry-aware VAE for better latent space modeling.

This paper reviews Bayesian methods for sparsity-aware modeling.

Modularity-aware GAE and VGAE improve community detection and link prediction.

New framework for evaluating multiclass classifier calibration.

Unified framework for planning under uncertainty using variational inference.

In this paper, we analyze energy-harvesting adaptive diffusion networks for a distributed estimation problem. In order to wisely manage the available energy resources, we propose a scheme where a censoring algorithm is jointly applied over the diffusion strategy. An energy-aware variation of a diffusion algorithm is us…

Conformal-DP improves differential privacy on manifold data by calibrating perturbations based on local densities.

Scientific documents rely on both mathematics and text to communicate ideas. Inspired by the topical correspondence between mathematical equations and word contexts observed in scientific texts, we propose a novel topic model that jointly generates mathematical equations and their surrounding text (TopicEq). Using an e…

Attention mechanism is effective in both focusing the deep learning models on relevant features and interpreting them. However, attentions may be unreliable since the networks that generate them are often trained in a weakly-supervised manner. To overcome this limitation, we introduce the notion of input-dependent unce…

VDA improves disentanglement of latent representations in complex signals.

GH-PID uses guided harmonic paths for efficient SOT with interpretable diagnostics.

Noise-aware Bayesian inference framework for locally private data collection.