New methods improve autotuning of exascale applications by 1.5x.
problem Finding optimal performance parameters for exascale applications.
method Multitask and transfer learning for autotuning.
result Average 1.5x improvement in application runtime.
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,878 papers · 148 categories
Trend · papers per month
13 results for “Autotuning”
Autotune optimizes Lasso tuning parameters efficiently and accurately.
problem Efficiently selecting Lasso tuning parameters in high-dimensional models.
method Alternates optimizing regression coefficients and noise standard deviation.
result Autotune outperforms existing methods in low signal-to-noise regimes.
Autotune optimizes machine learning models with multiple objectives and constraints.
problem Building and selecting optimal machine learning models is a multi-objective optimization problem.
method Derivative-free optimization methods and multi-level parallelism in a distributed computing environment.
result Autotune efficiently captures Pareto fronts and guides the search to more promising regions.
Deep Autotuner corrects singing pitch using neural networks.
problem Automatic pitch correction for singing performances.
method Neural network model trained on spectrograms of singing and accompaniment.
result Neural network predicts continuous pitch shifts, allowing for improvisation and harmonization.
Machine learning applications often require hyperparameter tuning. The hyperparameters usually drive both the efficiency of the model training process and the resulting model quality. For hyperparameter tuning, machine learning algorithms are complex black-boxes. This creates a class of challenging optimization problem…
AutoTune learns wireless identifiers for facial recognition in real-world settings.
problem Facial recognition requires extensive user training, making it impractical for widespread deployment.
method Uses ambient wireless identifiers to train deep neural networks for facial recognition without user effort.
result Demonstrates a system that continuously refines facial recognition using wireless identifiers over time.
We describe a machine-learning approach to pitch correcting a solo singing performance in a karaoke setting, where the solo voice and accompaniment are on separate tracks. The proposed approach addresses the situation where no musical score of the vocals nor the accompaniment exists: It predicts the amount of correctio…
Deep RL optimizes compiler passes for better performance.
problem Designing optimal compiler optimization sequences is hard and often suboptimal.
method Employed deep reinforcement learning to learn optimal pass orderings.
result Achieved up to 1.32x speedup on previously unseen programs.
New methods reduce private federated learning communication automatically.
problem Reducing communication in private federated learning.
method Automatic compression rate adjustment based on training error, using secure aggregation and differential privacy.
result Provable instance-optimal for mean estimation, achieving favorable compression rates.
Approximate nearest neighbor algorithms are used to speed up nearest neighbor search in a wide array of applications. However, current indexing methods feature several hyperparameters that need to be tuned to reach an acceptable accuracy--speed trade-off. A grid search in the parameter space is often impractically slow…
This paper improves federated learning efficiency by auto-tuning secure aggregation parameters.
problem Efficient communication in federated learning with quantized updates.
method Auto-tuning secure aggregation parameters based on random rotation properties.
result Improved communication efficiency in federated learning with secure aggregation.
New method for fair resource allocation in AI-aware networks with unknown utility functions.
problem Fair resource allocation in AI-aware communication networks with unknown utility functions.
method Distributed, data-driven bilevel optimization approach to learn surrogate utility functions.
result The proposed algorithm learns from data to autotune surrogate utility functions for unknown utility functions.
AgEBO-Tabular combines NAS and hyperparameter tuning for fast, high-performing tabular models.
problem Developing high-performing predictive models for large tabular data sets is challenging.
method Combines aging evolution NAS and asynchronous Bayesian optimization for hyperparameter tuning in data-parallel training.
result Automatically discovered neural network models outperform state-of-the-art AutoML ensembles in inference speed by two orders of magnitude.