arXiv research

SCTL scales causal domain adaptation without prior knowledge.

Meta-SAGE improves deep RL scalability for CO tasks by adapting pre-trained models to larger-scale problems.

New method calibrates LLMs for safety-critical tasks with scalable Bayesian inference.

Explosive growth in data and availability of cheap computing resources have sparked increasing interest in Big learning, an emerging subfield that studies scalable machine learning algorithms, systems, and applications with Big Data. Bayesian methods represent one important class of statistic methods for machine learni…

New scalable methods for unbalanced optimal transport improve efficiency and applicability.

Study improves scalability of cell-free massive MIMO networks by optimizing UE-AP association.

New scalable variational Bayes methods for Hawkes processes.

SASE improves attributed graph clustering for large graphs with linear time and space complexity.

Survey combines FL and control for better adaptability and privacy.

Images seen during test time are often not from the same distribution as images used for learning. This problem, known as domain shift, occurs when training classifiers from object-centric internet image databases and trying to apply them directly to scene understanding tasks. The consequence is often severe performanc…

A scalable GP model for online uncertainty quantification over graphs.

ALT transforms time series data for better classification.

Develops Bayesian filtering for online learning and related problems.

DABS uses a policy network to select experiments in high-dimensional design spaces.

Tensor networks help learn complex physical laws from data.

Bayesian optimization (BO) is a model-based approach for gradient-free black-box function optimization. Typically, BO is powered by a Gaussian process (GP), whose algorithmic complexity is cubic in the number of evaluations. Hence, GP-based BO cannot leverage large amounts of past or related function evaluations, for e…

New graph representation learning network improves scalability and feature integration.

While recent continual learning methods largely alleviate the catastrophic problem on toy-sized datasets, some issues remain to be tackled to apply them to real-world problem domains. First, a continual learning model should effectively handle catastrophic forgetting and be efficient to train even with a large number o…

Can we effectively learn a nonlinear representation in time comparable to linear learning? We describe a new algorithm that explicitly and adaptively expands higher-order interaction features over base linear representations. The algorithm is designed for extreme computational efficiency, and an extensive experimental …

Scalable solver reduces PDE uncertainty with active learning.

New method for scalable barycenter computation using Wasserstein gradient flows.

Paper introduces a new adaptive gradient method with gradient compression for distributed training.

We describe four algorithms for neural network training, each adapted to different scalability constraints. These algorithms are mathematically principled and invariant under a number of transformations in data and network representation, from which performance is thus independent. These algorithms are obtained from th…

SpeqNets improve graph neural networks by scaling and adapting to graph sparsity.

This work explores adaptations of successful multi-armed bandits policies to the online contextual bandits scenario with binary rewards using binary classification algorithms such as logistic regression as black-box oracles. Some of these adaptations are achieved through bootstrapping or approximate bootstrapping, whil…

RLGP model improves robustness and accuracy for discontinuous response surfaces.

ECPv2 optimizes Lipschitz functions efficiently and scalably.

Improved Thompson Sampling algorithms for bandits with tighter regret bounds.

New nonconvex regularizer speeds up low-rank matrix completion.

ABI adapts to graph data for fast, scalable inference.

Despite advances in scalable models, the inference tools used for Gaussian processes (GPs) have yet to fully capitalize on developments in computing hardware. We present an efficient and general approach to GP inference based on Blackbox Matrix-Matrix multiplication (BBMM). BBMM inference uses a modified batched versio…

The paper develops scalable variational inference for Bayesian neural networks under model and parameter uncertainty.

Diffusion-based classifiers such as those relying on the Personalized PageRank and the Heat kernel, enjoy remarkable classification accuracy at modest computational requirements. Their performance however is affected by the extent to which the chosen diffusion captures a typically unknown label propagation mechanism, t…

eva method improves RL models by adaptively creating prompts, boosting performance.

A scalable Gaussian process clustering method for large datasets.

The adjoint sensitivity method scalably computes gradients of solutions to ordinary differential equations. We generalize this method to stochastic differential equations, allowing time-efficient and constant-memory computation of gradients with high-order adaptive solvers. Specifically, we derive a stochastic differen…

The scalability of statistical estimators is of increasing importance in modern applications. One approach to implementing scalable algorithms is to compress data into a low dimensional latent space using dimension reduction methods. In this paper we develop an approach for dimension reduction that exploits the assumpt…

Develops a flexible deep autoencoding topic model with scalable hybrid Bayesian inference.

Optimal Transport (OT) naturally arises in many machine learning applications, yet the heavy computational burden limits its wide-spread uses. To address the scalability issue, we propose an implicit generative learning-based framework called SPOT (Scalable Push-forward of Optimal Transport). Specifically, we approxima…

A new meta-learning BO approach that bypasses surrogate models and directly learns task utility.

Novel method for scalable neural network-based blackbox optimization.

Bayesian neural networks (BNNs) have recently regained a significant amount of attention in the deep learning community due to the development of scalable approximate Bayesian inference techniques. There are several advantages of using Bayesian approach: Parameter and prediction uncertainty become easily available, fac…

Adaptive querying learns user psychometrics with AI personas.

Sparse Meta Networks adapt deep neural networks incrementally for fast learning.

New algorithm speeds up Gaussian process optimization.

Improves Gaussian process regression without bias.

EduQG generates better educational questions by pre-training on scientific text.

Graph neural networks learn decentralized controllers from data.