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.
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.
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.
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.
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. 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.
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.
For well over a quarter century, detection systems have been driven by models learned from input features collected from real or simulated environments. An artifact (e.g., network event, potential malware sample, suspicious email) is deemed malicious or non-malicious based on its similarity to the learned model at runt…
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…
Separating the short jobs from the long is a known technique to improve scheduling performance. In this paper we describe a method we developed for accurately predicting the runtimes classes of the jobs to enable this separation. Our method uses the fact that the runtimes can be represented as a mixture of overlapping …
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…
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.
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.
Distributed Stochastic Gradient Descent (SGD) when run in a synchronous manner, suffers from delays in waiting for the slowest learners (stragglers). Asynchronous methods can alleviate stragglers, but cause gradient staleness that can adversely affect convergence. In this work we present a novel theoretical characteriz…
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.
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.
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.
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. 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.
Flexible deep learning models for dynamic accuracy and speed trade-offs.
problem Dynamic accuracy and speed trade-offs in real-world applications.
method Training deep neural networks with a new method allowing flexible numerical precision during inference.
result Achieved comparable accuracy to dedicated models trained at the same precision with dynamic precision settings.
Improved computational efficiency for estimating Wasserstein distance.
problem Inefficient computation of Wasserstein distance for large samples.
method Developed Sample-Sketch-Solve paradigm using grid sketches.
result Approximates Wasserstein distance within ε error in ε^(-max(2, (d+1+o(1))/(1+α))) time.
Combines fast evaluation with Bayes consistency in nearest neighbors.
problem Balancing fast evaluation time with Bayes consistency in nearest neighbors.
method Combines locality-sensitive hashing (LSH) with a missing-mass argument.
result Fast and Bayes-consistent classifier with comparable risk decay rates.
A new method estimates generative model mappings using kernel transfer operators, reducing costs and improving performance.
problem Efficiently estimating mappings between known and unknown distributions in generative models.
method Adapting kernel transfer operators to estimate mappings, reducing computational costs.
result Significant runtime savings and good empirical performance compared to existing methods.
New method predicts outcomes even when some factors are not used in models.
problem Predicting outcomes under runtime confounding where some factors are unavailable.
method Doubly-robust procedure for counterfactual predictions.
result Method often outperforms competing approaches in runtime confounding.
Scorio.jl ranks systems from repeated tasks using various methods.
problem Evaluating and ranking systems from repeated responses to shared tasks.
method Common tensor-based interface for multiple ranking methods.
result Pilot experiments show stability and runtime scaling.
Max-convolution is an important problem closely resembling standard convolution; as such, max-convolution occurs frequently across many fields. Here we extend the method with fastest known worst-case runtime, which can be applied to nonnegative vectors by numerically approximating the Chebyshev norm $\| \cdot \|_\infty…
UMFI improves feature importance methods by reducing runtime and enhancing performance.
problem Improving feature importance methods to better explain causal and associative relationships in data.
method Introducing UMFI, which uses dependence removal techniques from AI fairness literature.
result UMFI outperforms MCI, especially in complex data scenarios, and reduces runtime from exponential to super-linear.
A new algorithm reduces online exp-concave optimization runtime.
problem Minimizing regret in online learning with exponentially concave losses.
method LightONS, a variant of Online Newton Step (ONS), reduces runtime to O ( d 2 T + d ω T log T ) O(d^2 T + d^ω\sqrt{T \log T}) O ( d 2 T + d ω T log T ) . result Optimal regret with reduced runtime to O ( d 2 T + d ω T log T ) O(d^2 T + d^ω\sqrt{T \log T}) O ( d 2 T + d ω T log T ) . A distributed algorithm for online multi-task learning reduces communication and runtime costs.
problem Heavy communication and high runtime complexity in online multi-task learning.
method Adaptive primal-dual algorithm that synchronizes data across geographically distributed tasks.
result The proposed algorithm achieves optimal regret and is effective on real-world datasets.
Improved algorithm for optimal stopping problems reduces runtime.
problem Optimal stopping problems with infinite time horizon and random discounting.
method Flexible forward improvement iteration with a variable look-ahead distance.
result The new algorithm converges and can significantly reduce runtime.
Improved biclustering algorithm reduces memory usage and runtime.
problem Efficiently enumerating maximal biclusters in numerical datasets.
method Online partitioning to guide biclustering results.
result RIn-Close_CVC3 reduces memory usage and runtime, handles missing values.
We developed a caching method to speed up concept learning in complex knowledge bases.
problem Complex concept learning requires many instance retrieval calls, increasing runtime.
method Semantics-aware caching that links concepts to instances via crisp set operations.
result Our cache reduces concept retrieval and learning runtime by an order of magnitude.
SDSR reconstructs species trees from genetic markers efficiently.
problem Challenges in reconstructing species trees from genetic data.
method Spectral divide-and-conquer approach based on graph theory.
result SDSR achieves up to 10-fold faster runtime with comparable accuracy.
Improved EXACT strategy reduces GNN memory consumption and runtime.
problem Efficiently training large-scale GNNs with reduced memory usage.
method Block-wise quantization of intermediate activation maps with improved variance minimization.
result Further reduction in memory consumption (>15%) and runtime speedup (5%) with similar performance trade-offs.
"How much energy is consumed for an inference made by a convolutional neural network (CNN)?" With the increased popularity of CNNs deployed on the wide-spectrum of platforms (from mobile devices to workstations), the answer to this question has drawn significant attention. From lengthening battery life of mobile device…