Benchmarked over 70 graph clustering algorithms.
problem Lack of comprehensive performance comparison for graph clustering algorithms.
method Evaluated 70+ graph clustering programs for runtime and quality on weighted and unweighted graphs, analyzed ground truth characteristics.
result Supply a start point for engineers and viewpoint for researchers.
Vecchia approximations provide the best accuracy-runtime trade-off for Gaussian process approximations.
problem High computational cost of Gaussian processes for large data sets.
method Systematic comparison of different Gaussian process approximations.
result Vecchia approximations consistently provide the best accuracy-runtime trade-off.
QBSD optimizes KPI forecasting for RAN networks with fast runtime and accuracy.
problem Efficiently forecasting KPIs for RAN networks with dynamic operating ranges.
method Quartile-Based Seasonality Decomposition (QBSD) for live single-step forecasting.
result QBSD outperforms other methods in runtime efficiency and forecast accuracy.
This paper compares AI performance in native vs. browser-based implementations.
problem Performance demands in AI applications, especially client-side.
method Comparison study between native code and browser-based (JS, ASM.js, WebAssembly) implementations.
result Current runtime optimizations push browser performance close to native binary.
A new method selects variables for random survival forests using maximally selected rank statistics.
problem Random survival forests can be biased in selecting variables, especially for non-linear effects.
method Use maximally selected rank statistics for variable selection in random survival forests, comparing on p-value scale.
result The new method outperforms other approaches in prediction performance and computational speed.
New tests measure model goodness of fit with interpretable features.
problem Measuring relative goodness of fit between two models.
method Nonparametric, computationally efficient tests producing informative features.
result Test power matches state-of-the-art but is one order faster.
Model predicts counterfactuals under domain shift and inaccessible variables.
problem Runtime domain corruption impairs counterfactual prediction.
method Subsumes counterfactual prediction under domain adaptation, uses adversarial domain adaptation to reduce distribution disparity.
result VEGAN outperforms baselines in individual-level treatment effect estimation.
Paper improves job scheduling by accurately predicting runtime classes.
problem Improving scheduling performance by separating short jobs from long jobs.
method Uses a CART classifier trained on Gaussian mixture representations of job runtimes.
result Overall accuracy of 90% for separating short jobs from long jobs.
There has been a growing interest in using non-parametric regression methods like Gaussian Process (GP) regression for system identification. GP regression does traditionally have three important downsides: (1) it is computationally intensive, (2) it cannot efficiently implement newly obtained measurements online, and …
Serverless runtimes boost large-scale optimization efficiency.
problem Efficiently solving large-scale optimization problems.
method Master-worker setup with AWS Lambda, parallel optimization algorithm.
result Relative speedups up to 256 workers and efficiencies above 70% up to 64 workers.
Stochastic momentum methods trade compute efficiency for serial runtime.
problem Stochastic momentum methods trade compute efficiency for serial runtime.
method Stochastic HB and ASGD for consistent linear regression with Gaussian covariates.
result HB preserves SGD-level CE over a larger batch-size window, allowing larger batches to reduce serial runtime until HB reaches its deterministic accelerated scale.
Bayesian method predicts runtime metrics for fog manufacturing.
problem Accurate prediction of runtime performance metrics in fog manufacturing.
method Bayesian sparse regression for multivariate mixed responses.
result Enhanced prediction and statistical inferences of runtime metrics.
The runtime for Kernel Partial Least Squares (KPLS) to compute the fit is quadratic in the number of examples. However, the necessity of obtaining sensitivity measures as degrees of freedom for model selection or confidence intervals for more detailed analysis requires cubic runtime, and thus constitutes a computationa…
Asynchronous SGD can speed up training with a trade-off of gradient staleness.
problem Asynchronous SGD suffers from gradient staleness, affecting convergence error.
method Theoretical analysis of the error-runtime trade-off considering random straggling delays.
result A method of gradually varying synchronicity in distributed SGD is proposed and demonstrated.
New algorithm improves feature selection for streaming data.
problem Traditional OSFS methods assume all data available at runtime, but features and samples stream concurrently.
method Introduces Geometric Online Adaption (GOA) for concurrent streaming of features and samples.
result GOA outperforms SAOLA on various datasets and in the OSFS-SS setting.
This work tackles runtime complexity prediction for code, using machine learning and a new dataset.
problem Predicting runtime complexity of code is hard and mathematically impossible.
method Modelled as a machine learning task, using feature engineering and code embeddings, with a new dataset.
result Achieved state-of-the-art results in runtime complexity prediction.
Algorithm decides if two hyperbolic 3-manifolds are homeomorphic.
problem Determining if two hyperbolic 3-manifolds are homeomorphic.
method Algorithm finds hyperbolic structures and compares geometric manifolds.
result Algorithm runs in bounded time for triangulations with at most t t t tetrahedra. C-FAR automates clustering assessment for neural tracking.
problem Manual assessment of clusters by humans is slow and impractical for large datasets.
method C-FAR uses automated feedback queries to select optimal clustering from multiple algorithms.
result C-FAR produces near-perfect clustering on simulated neural data.
Paper optimizes PCA for fairness using MMD and Stiefel manifold optimization.
problem Fair principal component analysis (PCA) to minimize MMD between protected classes.
method Formulates fair PCA as non-convex optimization over Stiefel manifold, solves using REPMS with theoretical guarantees.
result Our approach outperforms prior work in fairness, explained variance, and runtime.
Using recycled samples can improve runtime for variance reduction methods.
problem Improving runtime efficiency with variance reduction methods.
method Recycling previously used samples instead of fresh ones for SDCA, SAG, and SVRG.
result Optimal sample size and integer number of epochs can be wasteful for SDCA.
Hierarchical Block Sparse Neural Networks improve both accuracy and runtime efficiency of sparse DNNs.
problem Inefficiency of sparse DNNs on regular parallel hardware due to irregular computation.
method Introducing HBsNN, a structured sparse neural network that balances accuracy and runtime efficiency.
result HBsNN achieves better runtime performance and accuracy than unstructured and highly structured sparse models.
Paper introduces HISA for efficient FHE computations.
problem Efficiently evaluating encrypted neural networks.
method Developed HISA for FHE applications, including compiler and runtime.
result Generated code is faster than hand-optimized implementations.
This work analyzes trade-offs between stragglers and gradient staleness in asynchronous distributed SGD.
problem Asynchronous distributed SGD suffers from gradient staleness that can affect convergence.
method Theoretical analysis of trade-offs between error and runtime, considering random straggler delays.
result Design of distributed SGD algorithms that balance stragglers and staleness, and a new learning rate schedule.
In many recent applications, data is plentiful. By now, we have a rather clear understanding of how more data can be used to improve the accuracy of learning algorithms. Recently, there has been a growing interest in understanding how more data can be leveraged to reduce the required training runtime. In this paper, we…
A new federated learning method speeds up training by selecting faster nodes first.
problem System heterogeneity and stragglers slow down federated learning.
method Adaptive selection of nodes based on data statistical characteristics.
result Significant speedup in wall-clock time compared to standard federated learning.
GNMR controls runtime stability in low-precision language model training.
problem Efficient low-precision training faces numerical risks at specific operators.
method GNMR compares gradient norms to historical means, applying bounded recovery actions.
result GNMR preserves high-fidelity quality with sparse, budgeted recovery.
Perhaps surprisingly, it is possible to predict how long an algorithm will take to run on a previously unseen input, using machine learning techniques to build a model of the algorithm's runtime as a function of problem-specific instance features. Such models have important applications to algorithm analysis, portfolio…
Paper improves detection accuracy using privileged training data.
problem Traditional detection systems rely on runtime features, limiting model accuracy.
method Adapting knowledge transfer, model influence, and distillation techniques to use training-time privileged information.
result Empirical evaluation shows up to 16.9% relative decrease in detection error.
Runtime neuron activation monitoring warns of decisions not supported by training data.
problem Ensuring neural network decisions are backed by training data in safety-critical applications.
method Create a monitor by storing neuron activation patterns from training data. In operation, compare new inputs to monitor for similar patterns.
result Monitors can detect a significant portion of misclassifications not supported by training data with a low false-positive rate.
Run2Survive uses survival analysis for algorithm selection, outperforming traditional methods.
problem Handling censored runtime data in algorithm selection.
method Decision-theoretic approach leveraging survival analysis for censored data.
result Run2Survive outperforms state-of-the-art AS approaches in experiments.
Validates neural networks inputs to protect against adversarial examples.
problem Ensuring neural networks robustness against adversarial attacks.
method Runtime local robustness verification based on normal distribution of robustness radii.
result Improves neural network accuracy and protects against adversarial examples.
Quantum machine learning can't achieve polylogarithmic runtimes, even with quantum data access.
problem Bounding the minimum number of samples required for supervised quantum learning.
method Statistical learning theory and quantum machine learning algorithms.
result Quantum machine learning algorithms for supervised learning have at most polynomial speedups over classical algorithms.
Paper compares AutoML methods for recommending classification algorithms.
problem Finding the best classification algorithm for a dataset.
method Four AutoML methods using Evolutionary Algorithms and CASH approach.
result EA-based methods, especially decision-tree induction, produce interpretable models.
A new runtime for AI agents calculates risks in real-time.
problem Managing risks and liabilities in autonomous AI actions.
method A time-consistent counterfactual actuarial layer with explicit underwriting boundaries.
result Establishes a well-defined toll and guarantees executed-action budgets.
Paper presents runtime-throttleable neural networks for resource-constrained devices.
problem Resource constraints in edge computing platforms.
method Runtime-throttleable neural networks using block-level gating.
result Smooth performance throttling with minimal accuracy loss.
New method for valid prediction intervals in counterfactual outcomes with runtime confounding.
problem Valid prediction intervals for counterfactual outcomes under runtime confounding.
method Debiased machine learning framework grounded in semiparametric efficiency theory.
result Prediction intervals achieve desired coverage rates with faster convergence compared to standard methods.
This paper improves neural network training performance by optimizing concurrency and operation scheduling.
problem Managing and scheduling fine-grained operations in neural network training for high performance.
method Extending TensorFlow runtime to enable automatic concurrency control and scheduling, using performance modeling.
result Achieved 33% average performance improvement on neural network models, up to 49%.
This paper presents Rudra, a parameter server based distributed computing framework tuned for training large-scale deep neural networks. Using variants of the asynchronous stochastic gradient descent algorithm we study the impact of synchronization protocol, stale gradient updates, minibatch size, learning rates, and n…
New algorithm reduces runtime for robust sparse mean estimation.
problem Efficiently estimating mean from corrupted data with sparse constraints.
method Subquadratic time algorithm using poly(k, log d, 1/ε) samples.
result First subquadratic time algorithm for robust sparse mean estimation.
NeuralPower predicts and optimizes energy consumption of CNNs.
problem Energy efficiency of CNNs during inference.
method Sparse polynomial regression for layer-wise energy prediction.
result NeuralPower achieves up to 68.5% improvement in prediction accuracy.
d3p package enables efficient Bayesian inference with differential privacy.
problem Efficiently performing Bayesian inference under differential privacy constraints.
method Differentially private variational inference for flexible probabilistic models.
result Achieves significant speed-up in runtime for complex models.
Compress++ speeds up distribution compression to near-linear time.
problem Accurately summarize a probability distribution using a small number of points efficiently.
method Introduces Compress++, a meta-procedure to speed up any thinning algorithm.
result Achieves n \sqrt{n} n points with O ( log n / n ) \mathcal{O}(\sqrt{\log n/n}) O ( log n / n ) integration error in O ( n log 3 n ) \mathcal{O}(n \log^3 n) O ( n log 3 n ) time and O ( n log 2 n ) \mathcal{O}( \sqrt{n} \log^2 n ) O ( n log 2 n ) space. Rewiring networks using discrete geometry improves GNN training accuracy and reduces runtime.
problem Inefficient information propagation between distant nodes in graph neural networks.
method Discrete analogues of classical geometric curvature to model and rewire networks.
result Classical geometric notions achieve state-of-the-art GNN training accuracy and significantly reduce runtime.
Framework insures AI actions with reserve capital, preventing loss.
problem Ensuring safety and accountability for AI actions with varying side effects.
method Developed Actuarial Action Interface (AAI) and Authority Frontier to price and gate AI actions.
result Found common refusal and release patterns across domains, with varying required reserve capital.
New DP algorithm improves privacy and efficiency for convex optimization.
problem Efficient, DP algorithms for convex optimization with strong excess risk bounds.
method Output perturbation for a broad class of tilted loss functions.
result Near optimal DP excess risk and runtime bounds for convex optimization.
Logical scaffolds enhance AI software quality.
problem Improving AI component quality in software.
method Logical scaffolds as a method to improve AI components.
result Logical scaffolds can improve AI beyond perception systems.
StruClus clusters large graph datasets efficiently and interpretably.
problem Clustering large-scale graph databases efficiently and interpretably.
method Frequent subgraph sampling, projection-based clustering, parallelization.
result StruClus achieves high quality clusterings with linear runtime growth and interpretability.
New methods find eigenvectors faster than Lanczos's method.
problem Finding the leading eigenvector efficiently.
method Coordinate-wise methods combining shift-and-invert with linear regression.
result Global convergence with runtime guarantees better than Lanczos's method.