This paper explains how batch normalization auto-tunes the regularization parameter based on data statistics.
problem Batch normalization accelerates deep learning training but the exact relationship to regularization is unclear.
method Theoretical analysis and empirical validation of batch normalization's role in auto-tuning the regularization parameter.
result Batch normalization auto-tunes the regularization parameter based on data statistics.
A framework for auto-tuning hyper-parameters in contextual bandit algorithms.
problem Auto-tuning hyper-parameters in real-time for contextual bandit algorithms.
method Proposes a Syndicated Bandits framework to learn multiple hyper-parameters dynamically.
result Achieves optimal regret bounds under certain scenarios and handles multiple contextual bandit algorithms.
Efficient auto-tuning for DR hyperparameters with BO.
problem Hyperparameter selection in DR for large-scale datasets.
method Bayesian optimization with surrogate model, normalization, subsampling.
result Robust and efficient hyperparameter selection for DR algorithms.
This paper uses machine learning to select kernels for machine learning models on various devices.
problem Traditional kernel auto-tuning is limited for machine learning research with changing network topologies and hyperparameters.
method Combines auto-tuning and machine learning to select kernels for SYCL on various devices.
result Initial results show high performance kernel selection with little developer effort.
A cost-efficient method for hyperparameter tuning using multi-fidelity Bayesian optimization.
problem Expensive hyperparameter tuning with limited knowledge transfer methods.
method Amortized Auto-Tuning (AT2) framework for multi-task, multi-fidelity Bayesian optimization.
result AT2 leads to the best hyperparameter recommendation and is more cost-efficient.
ATLAS adapts HMC step size and trajectory length for complex geometries.
problem Sampling complex geometries with constant step size HMC/NUTS.
method Adapts step size and trajectory length using local Hessian and no U-turn condition.
result ATLAS accurately samples complex geometries, outperforming NUTS.
Software and hardware co-design and optimization of HPC systems has become intolerably complex, ad-hoc, time consuming and error prone due to enormous number of available design and optimization choices, complex interactions between all software and hardware components, and multiple strict requirements placed on perfor…
MLtuner automatically tunes settings for training tunables (such as the learning rate, the momentum, the mini-batch size, and the data staleness bound) that have a significant impact on large-scale machine learning (ML) performance. Traditionally, these tunables are set manually, which is unsurprisingly error-prone and…
AutoInit automatically finds good neural network initialization.
problem Finding optimal neural network initialization is crucial but time-consuming.
method Uses Jacobian tuning to automatically adjust network hyperparameters.
result The method finds good initialization for various network architectures.
Paper adds a restart mechanism to a drawdown control policy for better trading performance.
problem Missed profitable opportunities when drawdown limit is close to reality.
method Integrates a data-driven restart mechanism into the drawdown modulation trading system.
result The restart mechanism improves trading performance even with transaction costs.
Kalman filters are routinely used for many data fusion applications including navigation, tracking, and simultaneous localization and mapping problems. However, significant time and effort is frequently required to tune various Kalman filter model parameters, e.g. process noise covariance, pre-whitening filter models f…
Meta-SAC automatically tunes SAC's entropy temperature for better exploration.
problem Exploration-exploitation dilemma in reinforcement learning.
method Meta-SAC uses metagradient and a novel meta objective to automatically adjust SAC's entropy temperature.
result Meta-SAC outperforms SAC-v2 by 10% on the humanoid-v2 task.
Deep Learning has established itself to be a common occurrence in the business lexicon. The unprecedented success of deep learning in recent years can be attributed to: abundance of data, availability of gargantuan compute capabilities offered by GPUs, and adoption of open-source philosophy by the researchers and indus…
Federated Learning enables mobile devices to collaboratively learn a shared inference model while keeping all the training data on a user's device, decoupling the ability to do machine learning from the need to store the data in the cloud. Existing work on federated learning with limited communication demonstrates how …
It has been reported repeatedly that discriminative learning of distance metric boosts the pattern recognition performance. A weak point of ITML-based methods is that the distance threshold for similarity/dissimilarity constraints must be determined manually and it is sensitive to generalization performance, although t…
Large-batch training approaches have enabled researchers to utilize large-scale distributed processing and greatly accelerate deep-neural net (DNN) training. For example, by scaling the batch size from 256 to 32K, researchers have been able to reduce the training time of ResNet50 on ImageNet from 29 hours to 2.2 minute…
AutoQuant addresses cryptocurrency backtesting fragility by modeling execution costs and improving strategy selection.
problem Fragile backtests of cryptocurrency perpetual futures ignoring microstructure frictions and execution costs.
method Execution-centric framework with Bayesian optimization, double screening, and strict T+1 semantics.
result Fee-only and zero-cost backtests overestimate returns, highlighting the importance of modeling execution costs.
STRIC detects anomalies in time series by analyzing residual signals.
problem Anomaly detection in multivariate time series data.
method End-to-end differentiable neural network architecture with Sequential Probability Ratio Test on residuals.
result STRIC outperforms state-of-the-art methods on multiple benchmarks.
ICE-Pruning accelerates deep neural network pruning by 9.61x.
problem Efficiently pruning deep neural networks while maintaining accuracy.
method Iterative pruning with automatic fine-tuning steps, freezing strategy, and custom learning rate scheduler.
result Significantly reduces pruning time by up to 9.61x.
Model-based reinforcement learning (MBRL) has been proposed as a promising alternative solution to tackle the high sampling cost challenge in the canonical reinforcement learning (RL), by leveraging a learned model to generate synthesized data for policy training purpose. The MBRL framework, nevertheless, is inherently…