SAFLe solves federated learning's trade-off between non-linearity and scalability.
problem Federated Learning's high communication overhead and performance collapse on non-IID data.
method SAFLe introduces a structured head of bucketed features and sparse, grouped embeddings, mathematically equivalent to a high-dimensional linear regression.
result SAFLe achieves a new state-of-the-art in analytic FL, outperforming linear AFL and multi-round DeepAFL.
Unified scalable GPCs for various likelihoods using additive noise.
problem Scalability issues and intractable inference in GPC for big data and non-Gaussian likelihoods.
method Additive noise to unify scalable GPCs for multiple likelihoods, using variational inference.
result Empirically superior results for binary/multi-class classification tasks with up to two million data points.
Paper proposes a private SGD algorithm to improve accuracy and reduce overhead.
problem Low model accuracy and high development/runtime overhead in private SGD.
method Integrates output perturbation for private SGD, addressing both issues.
result Significantly better test accuracy (up to 4X) than state-of-the-art algorithms.
In this paper we address the problem of performing statistical inference for large scale data sets i.e., Big Data. The volume and dimensionality of the data may be so high that it cannot be processed or stored in a single computing node. We propose a scalable, statistically robust and computationally efficient bootstra…
Sparse DNNs face scalability issues; MIT/IEEE/Amazon challenge analyzes best solutions.
problem Scalability issues in Sparse Deep Neural Networks (DNNs).
method Mathematically defined DNN inference computation, community submissions from various fields.
result Sparse DNN execution time, TmDNN, is strongly dependent on the number of operations, Nmop. S3VDC improves DC methods for scalability, stability, and simplicity.
problem Poor scalability, instability, and lack of simplicity in DC methods.
method Four algorithmic improvements: initial γ-training, periodic β-annealing, mini-batch GMM initialization, and inverse min-max transform. S3VDC incorporates all improvements. result S3VDC outperforms state-of-the-art methods on benchmark and industrial datasets.
Paper proposes scalable algorithm to estimate intervention targets in linear models.
problem Estimating intervention targets in linear models from observational and interventional data.
method The paper proposes a scalable algorithm that estimates intervention sites from the difference between precision matrices of observational and interventional datasets.
result The algorithm consistently identifies all intervention targets and updates observational Markov equivalence classes to interventional ones.
This paper improves GP for learning complex data distributions.
problem Vanilla Gaussian processes struggle with complex data distributions.
method Introduces scalable GP paradigms with latent variables and variational inference.
result Scalable modulated GPs, especially latent GPs, learn diverse data distributions better.
New protocol makes federated learning more scalable and private.
problem Securely aggregate data from distributed, private datasets.
method Proposes a new protocol for aggregation in the shuffled model that is more efficient in terms of communication and error.
result Achieves differential privacy guarantees with polylogarithmic scaling in the number of users.
NanoFlow reduces parameter complexity in normalizing flows.
problem Efficient parameter complexity in flow-based models.
method Single neural density estimator with flow indication embedding.
result Sublinear parameter complexity achieved.
Paper simplifies complex sports analytics models for better understanding.
problem Difficulty in interpreting deep learning models for sports analytics.
method Developed a linear model tree that mimics deep learning models and explains its knowledge.
result The linear model tree achieves high accuracy and provides actionable insights.
Sparse DNN challenge aims to improve graph data analysis.
problem Scalability issues in sparse data analysis.
method Mathematically defined DNN inference, vertex-centric and array-based implementations.
result Performance predictions based on simple hardware models.
A new node embedding method that adapts to graph structure.
problem Scalable node embedding for large graphs.
method Adaptive node similarity matrix for multilength paths.
result Superior performance in node classification, link prediction, and clustering.
BO method improved by density-ratio estimation for better efficiency and scalability.
problem Limitations in Bayesian optimization due to analytical tractability of predictive models.
method Reformulated Bayesian optimization by casting expected improvement as a binary classification problem.
result Improved efficiency and scalability of Bayesian optimization.
Tensor networks help learn complex physical laws from data.
problem Identifying non-linear dynamical laws from complex physical systems.
method Tensor network parameterizations and rank-adaptive optimization.
result Optimal tensor network models can be learned from data.
A fast and scalable deep learning model for analyzing fMRI data.
problem Challenges in modeling and analyzing large-scale fMRI data.
method Distributed deep Convolutional Autoencoder model leveraging multiple GPUs and Apache Spark.
result Efficient and scalable model for extracting hierarchical neuroscientific information from fMRI big data.
Efficiently augments triplet data for better data analytics.
problem Lack of direct pairwise distance information for data analysis.
method Triplets augmentation to infer hidden information from existing data.
result Improves quality of kernel-based and kernel-free data analytics.
A new algorithm for high-dimensional hedging problems.
problem High-dimensional, path-dependent hedging problems.
method Signature-based algorithm using operator-valued kernels and geometric rough paths.
result Theoretical guarantees on existence and uniqueness of a global minimum.
Gaussian processes (GP) are Bayesian non-parametric models that are widely used for probabilistic regression. Unfortunately, it cannot scale well with large data nor perform real-time predictions due to its cubic time cost in the data size. This paper presents two parallel GP regression methods that exploit low-rank co…
Gaussian processes (GP) are Bayesian non-parametric models that are widely used for probabilistic regression. Unfortunately, it cannot scale well with large data nor perform real-time predictions due to its cubic time cost in the data size. This paper presents two parallel GP regression methods that exploit low-rank co…
Improves BED scalability for implicit models.
problem Designing experiments for implicit models with intractable data distributions.
method Hybrid gradient approach combining variational MI estimator, ES, and SGA.
result Significantly improves scalability of BED for implicit models.
Survey of tensor completion algorithms for big data analytics.
problem Filling missing entries in tensors.
method Overview of recent tensor completion algorithms.
result Advances in tensor completion for big data.
A new method improves Bayesian deep learning by balancing scalability and accuracy.
problem Scalability issues in Bayesian neural networks.
method Collapsed inference scheme that performs Bayesian model averaging using collapsed samples.
result Significant improvements over existing methods in predictive performance and uncertainty estimation.
DGBO optimizes attributed graphs efficiently.
problem Optimizing graphs with rich contextual features.
method Deep graph neural network surrogate for scalable Bayesian optimization.
result DGBO scales linearly with observations and outperforms state-of-the-art methods.
Laplacian mixture models identify overlapping regions of influence in unlabeled graph and network data in a scalable and computationally efficient way, yielding useful low-dimensional representations. By combining Laplacian eigenspace and finite mixture modeling methods, they provide probabilistic or fuzzy dimensionali…
This paper reviews feature selection in KGs for improved ML model performance.
problem Improving feature selection in KGs for better machine learning model efficacy.
method Comprehensive review of feature selection methodologies in KGs.
result Advancement in scalability, accuracy, and interpretability of feature selection techniques.
Develops scalable autoencoder for document networks.
problem Sparse and skewed latent node representations in document relational networks.
method Combines graph Poisson factor analysis with Weibull-based graph inference networks.
result Extracts high-quality hierarchical latent document representations.
DABS uses a policy network to select experiments in high-dimensional design spaces.
problem Adaptive factorial screening in high-dimensional discrete design spaces.
method DABS learns a policy network offline to sequentially select experiments, incorporating sparsity and interactions via a spike-and-slab prior.
result DABS achieves superior accuracy and scalability over classical and Bayesian baselines under tight experimental budgets.
Proposes a method for kernel learning using feature maps.
problem Improving SVM margin through iterative refinement.
method Fourier-analytic characterization and iterative feature maps.
result Optimal and generalization guarantees for SVM margin improvement.
New method learns CTBN structures from incomplete data.
problem Learning CTBN structures from incomplete data.
method Cluster-variational approximations.
result Significantly improves scalability over existing methods.
Improved two-sample testing using L1 geometry for analytic kernels.
problem Detecting differences between distributions.
method Use L1 distance between kernel-based distribution representatives to improve testing power. result Better detection of differences between distributions using L1 norm. Bayesian method pools spatial neural data to improve tuning function estimates.
problem Interpreting neural activity with spatially adjacent neurons.
method Block Gibbs sampler that pools information between neurons.
result The method de-noises tuning function estimates while preserving sharp discontinuities.
A new algorithm speeds up sparse regression for discovering equations from data.
problem Learning governing equations from vast data with unsatisfying descriptions.
method SPRINT: a fast algorithm using bisection and analytic bounds to identify optimal rank-1 modifications.
result A calculation that would take millions of years can be done in a day.
New bounds enable training of probabilistic models for deep networks.
problem Training scalable latent variable models for deep networks.
method Introducing new variational bounds for specific output layers of neural networks.
result Analytical bounds for certain output layers allow training without re-parameterization or Monte Carlo approximations.
Accelerates data loading in deep neural network training by 30x.
problem Data loading is a bottleneck in deep neural network training.
method Locality-aware data loading method using software caches.
result More than 30x speedup in data loading.
Edge devices learn directly from personal data using spiking networks.
problem Processing personal data on edge devices with low latency and energy efficiency.
method Spiking Neural Networks for local training on edge devices.
result Spiking networks enable efficient local training on edge devices without scalability limitations.
New SGMCMC method controls bias in SSMs for long time series.
problem Inference in SSMs is computationally prohibitive for long time series.
method Proposed new stochastic gradient estimators to control bias in SSMs.
result Developed novel SGMCMC samplers for various SSM types.
WHAI combines autoencoding and MCMC for scalable topic modeling.
problem Training scalable deep topic models for big corpora.
method Develops a hybrid autoencoding inference network for deep latent Dirichlet allocation.
result WHAI achieves both scalability and speed in topic inference.
Method for initializing Gaussian mixtures for variational inference with multi-modal distributions.
problem Challenges in variational inference with Gaussian mixtures due to multimodality and nonconvex loss functions.
method Optimization to find local maxima, local Gaussian approximations, and constrained least squares regression.
result Robust initialization improves variational inference performance and scalability.
SVGP KAN integrates sparse variational GP with KANs for scalable probabilistic inference.
problem Lack of probabilistic outputs in standard KANs and cubic scaling of Gaussian Process methods.
method Sparse Variational GP-KAN combines KAN topology with sparse variational inference and permutation-based importance analysis.
result Enables probabilistic KANs to handle larger datasets with linear computational complexity.
Unified framework interprets SSL models, revealing biases.
problem Interpreting black-box SSL models for transparency.
method KREPES framework using Representer Landmarks and Nyström approximation.
result Direct audit of SSL latent space without supervision.
A new method optimizes complex engineering designs under uncertainty efficiently.
problem Optimizing large, uncertain engineering designs with limited resources.
method Multi-level informed optimization via decomposed Kriging.
result Significantly faster and more accurate optimization compared to state-of-the-art methods.
New method discovers time series motifs under DTW, significantly reducing computations.
problem Discovering time series motifs under DTW is computationally challenging.
method Exact scalable method using novel lower bounds hierarchy.
result Prunes up to 99.99% of DTW computations under realistic settings.
Optimal Volt/VAR control rules are designed using deep neural networks.
problem Designing optimal Volt/VAR control rules for distributed energy resources (DERs).
method Formulate optimal rule design as a bilevel program, then reformulate it as training a deep neural network (DNN). Use proximal gradient descent (PGD) iterations to emulate Volt/VAR dynamics.
result The proposed solution can be adapted to single/multi-phase feeders and achieves enhanced steady-state voltage profiles.
A scalable approach to analyze daily EHR data for causal inference.
problem Inference challenges in analyzing daily EHR data due to computational cost.
method Developed a fast and scalable targeted learning approach using longitudinal TMLE and xgboost/h2o.
result Demonstrated the practical impact of using 90-day intervals for inference.
The paper proposes a scalable framework for uncertainty quantification and propagation in surrogate-based Bayesian inference.
problem Uncertainty in surrogate models and its impact on inference and decision-making.
method Bayesian inference methods for surrogate models with measurement data.
result Scalable framework for uncertainty quantification and propagation in surrogate models.
Unified framework for differentiable graph partitioning with probabilistic cuts.
problem Lack of general guarantees and principled gradients in prior probabilistic relaxations of graph cuts.
method Unified probabilistic framework covering a wide class of cuts, including Normalized Cut, with tight analytic upper bounds.
result Rigorous, numerically stable foundation for scalable, differentiable graph partitioning.
This paper proposes a distributed Bayesian method for piecewise sparse linear models.
problem High computational cost in simultaneous model selection for piecewise linear models.
method Distributed factorized asymptotic Bayesian (FAB) inference on distributed memory architectures.
result Achieves high prediction accuracy and performance scalability.