RNNs improve predictive precompute for faster user interface response times.
problem Improving user interface response times in mobile and web applications.
method Application of recurrent neural networks (RNNs) for predictive precompute.
result RNN models improve prediction accuracy and reduce computational cost.
FastMuyGPs speeds up GP predictions for large datasets.
problem High cost of Gaussian process predictions for large data.
method Combines cross-validation, batching, nearest neighbors sparsification, and precomputation.
result Superior accuracy and competitive runtime compared to other methods.
Method predicts multistable system states from sparse measurements.
problem Predicting multistable system states from limited data.
method Semi-supervised classification with SPML optimization.
result 95% accuracy in predicting reaction-diffusion equation states.
We are motivated by large scale submodular optimization problems, where standard algorithms that treat the submodular functions in the \emph{value oracle model} do not scale. In this paper, we present a model called the \emph{precomputational complexity model}, along with a unifying memoization based framework, which l…
Paper proposes a method to identify negative transfers in multitask learning using surrogate models.
problem Identifying subsets of source tasks that improve target task performance in multitask learning.
method Surrogate modeling to precompute multitask learning performances and approximate them with a linear regression model.
result The approach predicts negative transfers from multiple source tasks to target tasks more accurately than existing methods.
Limiting the model size of a kernel support vector machine to a pre-defined budget is a well-established technique that allows to scale SVM learning and prediction to large-scale data. Its core addition to simple stochastic gradient training is budget maintenance through merging of support vectors. This requires solvin…
A method to minimize regret in multi-agent control systems with adversarial disturbances.
problem Optimal control of dynamical systems with adversarial disturbances and multiple agents.
method Reduction from online convex optimization to a distributed algorithm for multi-agent control.
result The resulting distributed algorithm has low regret relative to the optimal precomputed joint policy.
Predicting potential credit default accounts in advance is challenging. Traditional statistical techniques typically cannot handle large amounts of data and the dynamic nature of fraud and humans. To tackle this problem, recent research has focused on artificial and computational intelligence based approaches. In this …
Item neighbourhood methods for collaborative filtering learn a weighted graph over the set of items, where each item is connected to those it is most similar to. The prediction of a user's rating on an item is then given by that rating of neighbouring items, weighted by their similarity. This paper presents a new neigh…
Computer algorithms are written with the intent that when run they perform a useful function. Typically any information obtained is unknown until the algorithm is run. However, if the behavior of an algorithm can be fully described by precomputing just once how this algorithm will respond when executed on any input, th…
Expanding the receptive field to capture large-scale context is key to obtaining good performance in dense prediction tasks, such as human pose estimation. While many state-of-the-art fully-convolutional architectures enlarge the receptive field by reducing resolution using strided convolution or pooling layers, the mo…
Deep neural network approximates flow averages for rough walls in multiscale simulations.
problem Approximating flow averages in rough-wall Stokes flow simulations.
method Fourier neural operator for local averages, parameterized by local wall geometry.
result Stable and accurate HMM solution with reduced micro problem solving cost.
A benchmark for NLP models trained on text datasets.
problem Limited access to high-performance clusters for NAS experiments.
method Created a search space for recurrent neural networks on text datasets and trained 14k architectures.
result Demonstrated the potential of precomputed NAS results for NLP.
A new GNN model SPIN achieves state-of-the-art performance on diverse real-world datasets.
problem Graph classification efficiency and accuracy.
method Parallel neighborhood aggregations (PA-GNNs) and SPIN model.
result SPIN model achieves state-of-the-art performance on diverse real-world datasets.
A method for non-parametric conditional distribution estimation using CRPS-optimal binning.
problem Non-parametric conditional distribution estimation.
method Partitioning covariate-sorted observations into bins to minimize LOO-CRPS, selecting K by K-fold cross-validation of test CRPS.
result Produces narrower prediction intervals with near-nominal coverage compared to split-conformal competitors.
Framework optimizes battery storage for markets by separating long-term degradation from short-term market dynamics.
problem Intractable computation due to timescale mismatch between battery degradation and market dynamics.
method Approximate dynamic programming with value function approximation and pseudo-time encoding.
result Policy outperforms benchmarks in real-time market scenarios.
We propose a new method to efficiently compute load-flows (the steady-state of the power-grid for given productions, consumptions and grid topology), substituting conventional simulators based on differential equation solvers. We use a deep feed-forward neural network trained with load-flows precomputed by simulation. …
DeepVol uses high-frequency data to forecast volatility, outperforming traditional methods.
problem Improving volatility forecasting using high-frequency data.
method Dilated Causal Convolutions applied to high-frequency financial time-series.
result DeepVol outperforms traditional methods in forecasting day-ahead volatility.
Novel framework for efficient entity alignment labeling.
problem Efficient labeling of entity alignments in knowledge graphs.
method Active and passive learning strategies to select informative instances.
result Passive learning achieves comparable performance to active learning.
Enhanced tabular benchmarks for energy-efficient neural architecture search.
problem Energy consumption in deep learning models.
method Introducing EC-NAS, an enhanced tabular benchmark with energy consumption data.
result EC-NAS reveals a balance between energy usage and accuracy in neural architecture search.
Let X be a data matrix of rank ρ, whose rows represent n points in d-dimensional space. The linear support vector machine constructs a hyperplane separator that maximizes the 1-norm soft margin. We develop a new oblivious dimension reduction technique which is precomputed and can be applied to any input matrix X. We pr…
The predictive quality of machine learning models is typically measured in terms of their (approximate) expected prediction accuracy or the so-called Area Under the Curve (AUC). Minimizing the reciprocals of these measures are the goals of supervised learning. However, when the models are constructed by the means of em…
A training-free message passing module improves hypergraph neural networks.
problem Computational intensive training process in hypergraph neural networks.
method Decoupling hypergraph structural information from model learning stage.
result TF-HNN achieves superior performance and training efficiency.
LASE learns graph embeddings by unrolling GD iterations into a neural network.
problem Learning graph embeddings from graph inputs.
method Truncating and interpreting GD iterations as layers in a GNN.
result LASE outperforms eigendecomposition routines and GNNs in link prediction and node classification.
Signatory calculates signature and logsignature transforms efficiently on CPU and GPU.
problem Efficient computation of signature and logsignature transforms for machine learning.
method CPU and GPU parallelism, backpropagation, efficient precomputation strategies, algorithmic improvements.
result Substantial speedups on CPU and GPU, including real-world applications.
A fast calibration method for rough volatility models with jumps.
problem Calibrating stochastic volatility models to market data efficiently.
method Structure-preserving approach: split pricing formula, precompute data-independent integrals, and approximate market-dependent remainder with neural networks.
result Calibration achieves high accuracy and speed, and a pure-jump rough volatility model adequately captures VIX dynamics.
New Lie group approach for envelope surface computation.
problem Efficient computation of envelope surfaces.
method Interpreting surfaces as curves in Lie group spaces, leveraging Lie group and algebra formalisms.
result Explicit rational parameterization of cone envelope surfaces and solution to trimming problem.
RFSVM uses learned RF similarity for HDLSS classification.
problem High dimension, low sample size classification problems.
method Transposes RFD approach to HDLSS classification using RF similarity as SVM kernel.
result RFSVM outperforms existing methods for HDLSS problems.
Paper develops fast, flexible Hawkes process inference for space-time data.
problem Capturing self-exciting, clustering spatio-temporal data.
method Finite support kernels, discretization, precomputations, ℓ2 gradient-based solver. result Statistically accurate and fast inference for space-time Hawkes processes.
FALL improves local model training with anchor regularization.
problem Efficient local model training in regression tasks.
method Regularization with precomputed anchor models, closed-form solution.
result FALL outperforms network Lasso in accuracy with significantly less training time.
Metric learning methods for dimensionality reduction in combination with k-Nearest Neighbors (kNN) have been extensively deployed in many classification, data embedding, and information retrieval applications. However, most of these approaches involve pairwise training data comparisons, and thus have quadratic computat…
A new method for graph neural networks speeds up inference and training.
problem Challenges in constructing mini-batches for large graphs in graph neural networks.
method Theoretical model of batch construction via maximizing influence score of nodes on outputs.
result Accelerates inference by up to 130x compared to previous methods.
Adversarial training, in which a network is trained on both adversarial and clean examples, is one of the most trusted defense methods against adversarial attacks. However, there are three major practical difficulties in implementing and deploying this method - expensive in terms of extra memory and computation costs; …
Paper speeds up GP inference by reducing precision matrix computation.
problem High computational complexity in computing kernel precision matrices.
method Splitting precision matrix into Hankel-Toeplitz matrices and computing only unique entries.
result Precision matrix computation reduced from O(NM2) to O(NM). The model uses signatures to accurately calibrate SPX and VIX options without jumps or rough volatility.
problem Joint calibration of SPX and VIX options without jumps or rough volatility.
method The approach uses a stochastic volatility model with signatures of polynomial diffusions to price and calibrate SPX and VIX options.
result Highly accurate calibration results for SPX and VIX options without adding jumps or rough volatility.
Efficient graph neural networks for large graphs without sampling.
problem Efficiently learning from large graphs like social networks.
method Inception graph neural networks using scalable graph convolutional filters.
result Significantly faster training and inference times compared to state-of-the-art methods.
We give a new consistent scoring function for structure learning of Bayesian networks. In contrast to traditional approaches to score-based structure learning, such as BDeu or MDL, the complexity penalty that we propose is data-dependent and is given by the probability that a conditional independence test correctly sho…
Modern deep reinforcement learning methods have departed from the incremental learning required for eligibility traces, rendering the implementation of the λ-return difficult in this context. In particular, off-policy methods that utilize experience replay remain problematic because their random sampling of minibatch…
METASET selects diverse unit cells for efficient data-driven metamaterial design.
problem Imbalanced datasets in unit cells can bias data-driven metamaterial design.
method METASET uses similarity metrics and DPPs to select diverse subsets of unit cells.
result Smaller, diverse subsets improve search process and structural performance.
T-EMDE bridges the heterogeneity gap between image and text modalities.
problem Finding similarities between image and text modalities with non-related feature spaces.
method Inspired by EMDE, T-EMDE uses sketches for multimodal operations, avoiding self-attention's quadratic complexity.
result T-EMDE achieves state-of-the-art results and reduces model latency.
New method uses SoS densities and α-divergences for efficient sequential transport maps.
problem Efficiently generating samples from approximated densities.
method Sequential transport maps using Sum-of-Squares (SoS) densities and α-divergences.
result Convex optimization problems with efficient semidefinite programming solutions.
Genie clusters faster and resists outliers.
problem Hierarchical clustering's sensitivity to outliers and slow computation.
method Genie uses an economic inequity measure to link clusters, balancing speed and quality.
result Genie outperforms other linkage methods in clustering quality and speed.
Soft diamond regularizers improve deep learning performance and sparsity.
problem Improving deep learning performance and sparsity of trained weights.
method New soft diamond synaptic weight priors based on thick-tailed symmetric alpha stable probability curves.
result Soft diamond regularizers outperform state-of-the-art methods in deep learning tasks.
Study efficient pricing for barrier options in stochastic-volatility models with leverage correction.
problem Barrier options are sensitive to volatility dynamics, especially leverage, making accurate pricing difficult.
method Developed a class of continuous-path stochastic-clock volatility models and a systematic small-ρ expansion to incorporate leverage.
result Transform-only pricing formulas for barrier derivatives are fast and numerically stable, even for negative leverage.
Fuzzy prediction sets generalize binary predictions to include elements at varying confidence levels.
problem Binary prediction sets are limited; fuzzy prediction sets offer richer guarantees.
method Generalize prediction sets to fuzzy sets, showing they are e-values with merging properties.
result Optimal e-values lead to optimal fuzzy prediction sets, including optimal conformal prediction.
This paper re-examines conformal e-prediction and its advantages over conformal prediction.
problem The relationship between conformal prediction and conformal e-prediction.
method Systematic re-examination of conformal prediction and conformal e-prediction from a modern perspective.
result Conformal e-prediction has advantages such as ease of designing conditional predictors and guaranteed validity of cross-predictors.
Two new methods improve efficiency of conformal predictive systems.
problem Efficiency of conformal predictive systems in regression problems.
method Split conformal predictive systems and cross-conformal predictive systems.
result Cross-conformal predictive systems are more efficient but not guaranteed valid.
Self-calibrating conformal prediction improves interval efficiency and offers a practical alternative.
problem Improving the reliability and uncertainty quantification of machine learning predictions.
method Combines Venn-Abers calibration and conformal prediction for binary and regression problems.
result Improves interval efficiency through model calibration and offers practical alternatives.