arXiv research

Differential Evolution outperforms SMAC in hyperparameter tuning.

TNP uses historical data to optimize hyperparameters faster.

Paper develops an efficient approach to reduce HPO time.

OMLE combines optimism and MLE for efficient sequential decision making.

Greedy algorithm performs well in online matching despite non-i.i.d. connections.

One of the most tedious tasks in the application of machine learning is model selection, i.e. hyperparameter selection. Fortunately, recent progress has been made in the automation of this process, through the use of sequential model-based optimization (SMBO) methods. This can be used to optimize a cross-validation per…

Constructs classifiers for neural networks with specific data configurations.

RL agent outperforms model-based approach in detecting price manipulation.

Bayesian optimization (BO) aims to minimize a given blackbox function using a model that is updated whenever new evidence about the function becomes available. Here, we address the problem of BO under partially right-censored response data, where in some evaluations we only obtain a lower bound on the function value. T…

Recent sequential pattern mining methods have used the minimum description length (MDL) principle to define an encoding scheme which describes an algorithm for mining the most compressing patterns in a database. We present a novel subsequence interleaving model based on a probabilistic model of the sequence database, w…

New SMC algorithm reduces memory usage for online clustering.

We study a budgeted hyper-parameter tuning problem, where we optimize the tuning result under a hard resource constraint. We propose to solve it as a sequential decision making problem, such that we can use the partial training progress of configurations to dynamically allocate the remaining budget. Our algorithm combi…

Algorithm optimizes ε-SVR with MAPE loss and sample-dependent constraints.

SMAC method optimizes tree-boosting hyperparameters best.

Optimistic RL algorithms are simplified for deep RL with competitive performance.

The paper improves Bayesian optimization by calibrating uncertainty estimates.

RecSim creates customizable simulation environments for RSs.

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…

New method optimizes clustering with better log-likelihood landscape.

This research improves interpretability in sequential explanations using mental models.

This review assesses deep-learning methods for complex sequential data.

Adaptive RL optimizes testing resource allocation for dynamic software environments.

We describe a methodology for modeling the performance of decision-level data fusion between different sensor configurations, implemented as part of the JIEDDO Analytic Decision Engine (JADE). We first discuss a Bayesian network formulation of classical probabilistic data fusion, which allows elementary fusion structur…

A new method reduces hyperparameter tuning evaluations by using sequential tests.

A new tree-based model improves uncertainty estimation in sequential optimization.

A multi-step model reduces compounding errors in reinforcement learning.

Algorithm reduces audit costs by identifying best service configurations from biased textual evidence.

Adaptive tuning of portfolio selection parameters improves performance in volatile markets.

We propose a parallel-data-free voice-conversion (VC) method that can learn a mapping from source to target speech without relying on parallel data. The proposed method is general purpose, high quality, and parallel-data free and works without any extra data, modules, or alignment procedure. It also avoids over-smoothi…

OP3 models entities for better task generalization in reinforcement learning.

Designing the architecture for an artificial neural network is a cumbersome task because of the numerous parameters to configure, including activation functions, layer types, and hyper-parameters. With the large number of parameters for most networks nowadays, it is intractable to find a good configuration for a given …

Conventional wisdom holds that model-based planning is a powerful approach to sequential decision-making. It is often very challenging in practice, however, because while a model can be used to evaluate a plan, it does not prescribe how to construct a plan. Here we introduce the "Imagination-based Planner", the first m…

Adaptive Bayesian Optimization for resource-constrained experiments with switching costs.

Surveying topological complexity of graph configurations, unifying traditional and modern approaches.

In recent years, deep generative models have been shown to 'imagine' convincing high-dimensional observations such as images, audio, and even video, learning directly from raw data. In this work, we ask how to imagine goal-directed visual plans -- a plausible sequence of observations that transition a dynamical system …

New method designs experiments robustly for nonlinear estimation, improving parameter knowledge.

Simple method improves exploration in various decision problems.

Auto-CASH uses Deep Q-Network to automatically select machine learning algorithms.

A new method for constrained Bayesian optimization using Max-Value Entropy Search.

Develops adaptive algorithms for sustainable fertilizer use in agriculture.

Models of complex systems are often formalized as sequential software simulators: computationally intensive programs that iteratively build up probable system configurations given parameters and initial conditions. These simulators enable modelers to capture effects that are difficult to characterize analytically or su…

Graph braid groups' complexity stabilizes for most graphs.

POLAR optimizes treatment strategies in dynamic settings with statistical guarantees.

DRL agents learn to trade Intel stock with stable positive returns.

Survey of integrating planning and learning in model-based reinforcement learning.

Algorithm maximizes rewards with a budget and giving up option.

Adapts MBDOE for real-time parameter estimation in complex systems.

Hybrid Bayesian MOT uses neural networks to improve model aspects, achieving state-of-the-art performance.