Memory-efficient learning for large-scale imaging systems.
problem Memory limitations in GPUs for real-world large-scale inverse problems.
method Exploits reversibility of network layers to enable data-driven design.
result Demonstrated on small-scale and large-scale real-world systems.
We present Distributed Equivalent Substitution (DES) training, a novel distributed training framework for large-scale recommender systems with dynamic sparse features. DES introduces fully synchronous training to large-scale recommendation system for the first time by reducing communication, thus making the training of…
Scale of data and scale of computation infrastructures together enable the current deep learning renaissance. However, training large-scale deep architectures demands both algorithmic improvement and careful system configuration. In this paper, we focus on employing the system approach to speed up large-scale training.…
New method speeds up learning of complex dynamical systems.
problem Efficiently learning large-scale dynamical systems from finite data.
method Random projections (sketching) to boost kernel-based Koopman operator estimators.
result The proposed estimators maintain accuracy while significantly reducing computation time.
Real time large scale streaming data pose major challenges to forecasting, in particular defying the presence of human experts to perform the corresponding analysis. We present here a class of models and methods used to develop an automated, scalable and versatile system for large scale forecasting oriented towards saf…
Bayesian regularization tackles collinearity in large-scale systems with correlated inputs.
problem Collinearity in large-scale linear systems identification due to correlated inputs.
method Bayesian regularization with stable spline covariance and Markov chain Monte Carlo scheme.
result Efficient reconstruction of impulse responses with high correlation among inputs.
BanditLP optimizes personalized recommendations for large-scale systems.
problem Optimizing personalized recommendations for large-scale systems with constraints.
method Unified neural Thompson Sampling for learning and large-scale linear programming for action selection.
result Consistent gains over strong baselines in experiments and business win in LinkedIn's email marketing system.
The paper simplifies influence computations for large-scale machine learning models.
problem Improving training efficiency and accuracy in large-scale models.
method Study influence functions, define memorization, simplify computations.
result Influence functions can be practical for large-scale models, indicating memorization.
New approach for large-scale distributed learning systems that improve generalization performance.
problem Transitioning from centralized to distributed AI systems for complex learning tasks.
method Self-organizing hierarchical structuring mechanism based on agglomerative clustering, hierarchical generalization, and personalized learning.
result Demonstrates better generalization performance compared to conventional federated learning algorithms.
Study evaluates machine learning methods for large-scale network reliability, revealing ANN's and PR's performance.
problem Tackles the NP-hard problem of approximating binary-state network reliability for large-scale systems.
method Compares 20 machine learning methods across three reliability regimes and evaluates their performance on large-scale networks.
result Large-scale networks with arc reliability ≥ 0.9 exhibit near-unity system reliability, enabling computational simplifications.
A new method speeds up ALS for recommender systems by subsampling key elements.
problem High computational cost of ALS for large-scale datasets.
method Core-elements subsampling method for efficient ALS approximation.
result Achieves similar accuracy with significantly reduced computational time.
Bayesian approach tackles collinearity in large-scale linear system identification.
problem Collinearity in large-scale linear system identification.
method Bayesian regularization framework with Gaussian process and stable spline kernel. Novel Markov chain Monte Carlo scheme.
result Efficiently reconstructs impulse responses posterior by dealing with collinearity.
New method infers causal factors from large-scale data without full graph reconstruction.
problem Inferring causal variables from large-scale systems without full causal graph reconstruction.
method Supervised learning on simulated data using a neural network and subsampled-ensemble inference.
result Efficiently identifies causal relationships in large-scale gene regulatory networks.
New machine learning method detects quantum separability in large-scale systems.
problem Deciding quantum separability of large-scale bipartite density matrices.
method Frank-Wolfe-based algorithm for finding nearest separable density matrices and classification of density matrices as separable or entangled.
result The method scales up to thousands of density matrices and achieves high quantum entanglement detection accuracy.
Paper introduces models to discover complex structures in large hypergraphs.
problem Understanding dependency structures in complex systems represented as hypergraphs.
method Probabilistic models treating classes of similar units as nodes in a latent hypergraph, using low-rank representations.
result Improves link prediction and discovers interpretable structures in diverse real-world systems.
We use Machine Learning (ML) and system identification validation approaches to estimate neural network models of large-scale Deformable Mirrors (DMs) used in Adaptive Optics (AO) systems. To obtain the training, validation, and test data sets, we simulate a realistic large-scale Finite Element (FE) model of a faceplat…
New method estimates bidirectional causal effects in large-scale systems.
problem Estimating bidirectional causal effects in systems with mutual dependence and heteroskedasticity.
method Heteroskedasticity-based identification with online kernel learning and random Fourier features.
result Superior accuracy and stability compared to single equation and polynomial approximations.
This paper optimizes slate decision systems for large action spaces.
problem Optimizing large-scale decision systems with arbitrary reward functions.
method A policy optimization framework with a novel relaxation of decision functions.
result Demonstrates the effectiveness of the proposed method on large action spaces.
CTR prediction in real-world business is a difficult machine learning problem with large scale nonlinear sparse data. In this paper, we introduce an industrial strength solution with model named Large Scale Piece-wise Linear Model (LS-PLM). We formulate the learning problem with L1 and L2,1 regularizers, leadin…
Two large medical dialogue datasets for improving healthcare.
problem Improving healthcare through better dialogue systems.
method Building two large-scale medical dialogue datasets: MedDialog-EN and MedDialog-CN.
result The datasets are the largest medical dialogue datasets to date.
We perform a large-scale simulation of an Ising-based financial market model that includes 300 asset time series. The financial system simulated by the model shows a fat-tailed return distribution and volatility clustering and exhibits unstable periods indicated by the volatility index measured as the average of absolu…
Gradient boosting decision tree (GBDT) is a widely-used machine learning algorithm in both data analytic competitions and real-world industrial applications. Further, driven by the rapid increase in data volume, efforts have been made to train GBDT in a distributed setting to support large-scale workloads. However, we …
Deep Retrieval learns a retrievable structure for efficient large-scale recommendations.
problem Efficiently retrieving top relevant candidates in large-scale recommendation systems.
method Deep Retrieval learns a retrievable structure directly from user-item interaction data, encoding candidates into a discrete latent space and optimizing a model to maximize accuracy.
result Deep Retrieval achieves almost the same accuracy as brute-force baseline and significantly outperforms ANN baselines in a live production system.
SEMASIA provides a large dataset of latent representations for model comparison.
problem Difficulty in comparing semantic structures across different neural network models.
method Collection of latent representations from 1700 pretrained models across various benchmarks.
result Consistent semantic organization across models and datasets.
The traditional offline approaches are no longer sufficient for building modern recommender systems in domains such as online news services, mainly due to the high dynamics of environment changes and necessity to operate on a large scale with high data sparsity. The ability to balance exploration with exploitation make…
We propose a generic algorithmic building block to accelerate training of machine learning models on heterogeneous compute systems. Our scheme allows to efficiently employ compute accelerators such as GPUs and FPGAs for the training of large-scale machine learning models, when the training data exceeds their memory cap…
Proposes SSL framework for improving item recommendations in large-scale systems.
problem Sparse feedback data for long-tail items in recommender systems.
method Multi-task self-supervised learning framework with data augmentation.
result Significant improvements in model performance, especially on slices lacking supervision.
A new network learns to prioritize messages for efficient multi-robot path planning.
problem Efficient path planning and coordination for large-scale multi-robot systems.
method Message-Aware Graph Attention Network (MAGAT) incorporating attention mechanisms.
result MAGAT achieves performance close to a coupled centralized expert algorithm.
Representation learning becomes especially important for complex systems with multimodal data sources such as cameras or sensors. Recent advances in reinforcement learning and optimal control make it possible to design control algorithms on these latent representations, but the field still lacks a large-scale standard …
FaStR improves scalability for time-aware RS with varying coefficients.
problem Limited applicability of structured regression models to large-scale data with categorical effects and many interactions.
method Combines structured additive regression and factorization approaches in a neural network-based model implementation.
result FaStR scales better and performs competitively with other time-aware RS in prediction performance.
Online retailers execute a very large number of price updates when compared to brick-and-mortar stores. Even a few mis-priced items can have a significant business impact and result in a loss of customer trust. Early detection of anomalies in an automated real-time fashion is an important part of such a pricing system.…
AnomalyCD discovers anomaly causes in large systems with binary flags, reducing computational burden.
problem Learning graphical causal models from large-scale binary anomaly data is computationally expensive.
method AnomalyCD uses anomaly data-aware causality testing, sparse data compression, and edge pruning.
result AnomalyCD reduces computation overhead and improves accuracy on binary anomaly datasets.
Modern investigation in economics and in other sciences requires the ability to store, share, and replicate results and methods of experiments that are often multidisciplinary and yield a massive amount of data. Given the increasing complexity and growing interaction across diverse bodies of knowledge it is becoming im…
Adaptive regularization prevents overfitting in large-scale sparse feature models.
problem Overfitting in models with large-scale sparse categorical features.
method Adaptive regularization of embedding layers' norm budget.
result Improves model performance within a single epoch and prevents multi-epoch performance degradation.
FibeRed reduces complex data dimensions while preserving topology.
problem Hard embedding of topologically complex datasets in low-dimensional Euclidean space.
method Modeling datasets with vector bundles, reducing fibers while preserving topology.
result FibeRed learns topologically faithful embeddings in lower dimensions than existing methods.
This paper surveys large-scale machine learning methods for efficient data analysis.
problem Efficiently processing large-scale data with machine learning models.
method Divided into three categories: model simplification, optimization approximation, and computation parallelism.
result Blueprint for future developments in large-scale machine learning.
This paper reviews recent advances in Gaussian process regression methods.
problem Handling uncertainties and scalability in large-scale systems with sparse data.
method Factorised Gaussian process methods, including hierarchical off-diagonal low-rank approximation and GP with Kronecker structures.
result These methods provide scalable solutions with inherent uncertainty assessment.
PALMS reconstructs large-scale networks efficiently with parallel computing.
problem Reconstructing large-scale latent networks from observed dynamics is computationally challenging.
method PALMS (Parallel Adaptive Lasso with Multi-directional Signals) framework for distributed network reconstruction.
result PALMS substantially reduces computational complexity and storage requirements.
We propose a probabilistic graphical model realizing a minimal encoding of real variables dependencies based on possibly incomplete observation and an empirical cumulative distribution function per variable. The target application is a large scale partially observed system, like e.g. a traffic network, where a small pr…
We present and analyze a model for the evolution of the wealth distribution within a heterogeneous economic environment. The model considers a system of rational agents interacting in a game theoretical framework, through fairly general assumptions on the cost function. This evolution drives the dynamic of the agents i…
CausalMan simulates complex causality for fair benchmarking.
problem Lack of realistic causal models with known data generating processes.
method Developed a physics-based simulator, CausalMan, for large-scale causality.
result Demonstrated inadequacy of state-of-the-art approaches and analyzed their performance.
New method approximates controllability of large networks from coarse summaries.
problem Controlling large-scale linear dynamical systems with incomplete network information.
method Algorithm using stochastic block model to estimate controllability from coarse summaries.
result Average controllability of fine-scale system can be well approximated by coarse-scale system.
Contemporary power grids are being challenged by rapid voltage fluctuations that are caused by large-scale deployment of renewable generation, electric vehicles, and demand response programs. In this context, monitoring the grid's operating conditions in real time becomes increasingly critical. With the emergent large …
Model captures neural activity related to behavior while separating internal computations.
problem Capturing neural activity related to behavior from complex brain recordings.
method Behavior-decomposed linear dynamical systems (b-dLDS) model.
result Improves over state-of-the-art models in disentangling behavior-related dynamics.
Two novel methods identify influential features in CMABs for better reward distribution.
problem Suboptimal features degrade rewards, interpretability, and efficiency in CMABs.
method Heterogeneous Incremental Effect (HIE) and Heterogeneous Distribution Divergence (HDD) methods.
result Consistent ability to identify influential HTE features, enhancing CMAB performance.
Paper models uncertainty in electricity and gas markets to assess its impact.
problem Addressing uncertainties in coupled electricity and gas markets.
method Integrated and stochastic optimisation approaches for large-scale energy systems.
result Quantifies the value of encoding uncertainty in models.
HollowFlow speeds up likelihood evaluation for large-scale models.
problem Prohibitive scaling of sample likelihood computations in flow-based models.
method Introduces HollowFlow, a flow-based generative model using a NoBGNN with a block-diagonal Jacobian structure.
result Achieves up to O(n^2) speed-up in likelihood evaluation for large systems.
The study introduces measures of collective mobility from aggregated OD data.
problem Understanding large-scale mobility patterns from aggregated data.
method Developed a framework using synthetic and real data to interpret network-level mobility.
result Aggregated mobility measures reveal network structure and flow constraints.