Proposes a method to imitate active learning heuristics for better performance.
problem The performance of active learning heuristics depends on the classifier model and data structure.
method Imitates the selection of the best active learning heuristic using DAGGER.
result Outperforms state-of-the-art imitation learners and heuristics on well-known datasets.
A new method learns link prediction heuristics from local subgraphs using GNN.
problem Link prediction in network-structured data.
method Developed a novel γ-decaying heuristic theory and a GNN-based algorithm to learn heuristics from local subgraphs.
result Unprecedented performance in link prediction across various problems.
Interactive weak supervision learns useful heuristics from user feedback.
problem Creating useful heuristics for large labeled datasets is tedious and subjective.
method Develops an interactive framework for learning heuristics from user feedback.
result Only a few feedback iterations are needed to train models without ground truth labels.
RLHO uses RL to generate better initial solutions for heuristic optimization.
problem High sample complexity in generating initial solutions for combinatorial optimization problems.
method RLHO framework that augments heuristic algorithms with RL to generate better initial solutions.
result RLHO outperforms baseline methods on bin packing problem.
Nemo improves WS learning pipeline by 20%.
problem Creating effective labeling heuristics for weak supervision.
method Interactive procedure for designing heuristics, strategic data selection, contextualization of heuristics.
result Improves WS learning pipeline by 20%.
The report evaluates heuristics for learning timescale graphical event models.
problem Lack of heuristics for determining hyper-parameters in timescale graphical event models.
method Proposed and evaluated different heuristics for hyper-parameter determination and refined an existing distance measure.
result Conclusions about the applicability of different heuristics on synthetic data.
This work explores the non-convex optimization in compressive learning and the performance of heuristics.
problem The challenge of learning from compressed representations in compressive learning.
method Numerical simulations of the non-convex optimization landscape and heuristic performance.
result Properties of the non-convex optimization landscape and heuristic performance are explored.
Deep RL learns 2-opt heuristics to improve TSP solutions.
problem Improving TSP solutions beyond initial heuristics.
method Deep reinforcement learning to learn 2-opt operations.
result Learned policies improve solutions faster than previous methods.
Recently two search algorithms, A* and breadth-first branch and bound (BFBnB), were developed based on a simple admissible heuristic for learning Bayesian network structures that optimize a scoring function. The heuristic represents a relaxation of the learning problem such that each variable chooses optimal parents in…
We propose a general approach to modeling semi-supervised learning (SSL) algorithms. Specifically, we present a declarative language for modeling both traditional supervised classification tasks and many SSL heuristics, including both well-known heuristics such as co-training and novel domain-specific heuristics. In ad…
A new heuristic for learning Markov network structure efficiently.
problem Complications in learning Markov networks, especially intractable computations and large parameter space.
method A computationally tractable greedy heuristic to limit the number of parameters.
result The method performs comparably well to state-of-the-art methods on real datasets.
Study combines A* and DNN for better pathfinding.
problem Limited applicability of A* in domains without good heuristics.
method Trains a DNN to represent heuristic for A* and integrates it.
result Significantly better performance in driving simulation.
Empirical analysis of deep learning heuristics like learning rate restarts and distillation.
problem Understanding the effectiveness and mechanisms of deep learning heuristics.
method Loss surface and representation analysis methods (mode connectivity and CCA) for empirical analysis.
result Learning rate warmup prevents training instability in deeper layers, and cosine annealing does not explain success.
New approach predicts credit default using machine learning and heuristics.
problem Predicting credit default in large datasets with dynamic nature.
method Combined heuristic and machine learning approaches.
result Approaches outperform existing state-of-the-art methods.
PAC-Bayes analysis explains sentence vector learning from unlabeled data.
problem Understanding and improving sentence vector learning from unlabeled data.
method PAC-Bayes bound analysis for transfer learning.
result Simple heuristics and new algorithms derived from PAC-Bayes analysis.
NeuRewriter learns to choose and rewrite heuristics in combinatorial problems.
problem Time-consuming tuning of heuristics in combinatorial optimization.
method NeuRewriter uses reinforcement learning to learn a policy for picking heuristics and rewriting solutions.
result NeuRewriter outperforms existing methods in various combinatorial tasks.
RL improves combinatorial optimization by automating heuristic search.
problem Hard combinatorial optimization problems with suboptimal solutions.
method Training RL agents to solve these problems.
result RL can outperform traditional algorithms in solving complex problems.
Declarative entropy constraints improve semi-supervised learning.
problem Improving semi-supervised learning performance.
method Declarative specification of entropy constraints for semi-supervised learning.
result Consistent improvements on SSL benchmarks, including a new state-of-the-art result.
Bayesian symbolic regression automates model discovery from data.
problem Learning closed-form mathematical models from data using heuristic methods.
method Probabilistic approach to symbolic regression, connecting to information theory and statistical physics.
result Probabilistic approach provides model plausibility and performance guarantees.
New algorithms for private data synthesis using heuristics.
problem Private data synthesis for complex functions.
method Developed algorithms using non-private oracles and certifiable heuristics.
result Efficient private data synthesis for broad classes of functions.
Decision tree learning heuristics fail even in smoothed analysis for complex targets.
problem Greedy decision tree learning heuristics fail for complex target functions in the smoothed analysis model.
method Construct counterexamples and analyze the behavior of heuristics in the smoothed setting and agnostic setting.
result Greedy decision tree learning heuristics can build trees of exponential depth before achieving high accuracy for certain complex target functions.
This work explores how to balance rule consistency and coverage for multi-label classification.
problem Balancing rule consistency and coverage for effective multi-label classification.
method Empirical study of rule learning heuristics in multi-label classification.
result The choice of heuristic for multi-label classification is crucial and depends on the performance measure.
Improves heuristics for routing problems using attention models.
problem Improving heuristics for combinatorial optimization problems, especially for routing problems.
method Proposed a model based on attention layers and trained it using REINFORCE with a simple greedy rollout.
result Significantly improved results for TSP and other routing problems, close to optimal or specialized algorithms.
New heuristics improve genetic programming's parent selection for classification problems.
problem Improving genetic programming's parent selection for classification tasks.
method Proposed three heuristics inspired by specific classifiers' characteristics, using similarity measures.
result Combination of agreement-based selection and random selection outperforms classical and state-of-the-art schemes.
Two heuristics solve dynamic multiple travelling salesmen problems.
problem Dynamic routing with unknown customers.
method Balanced dynamic closest vehicle heuristic and balanced dynamic assignment vehicle heuristic.
result Continuous approximation models for strategic dynamic routing.
Coral infers generative model structure from code heuristics.
problem Lack of labeled data for complex generative models.
method Static code analysis to infer model structure without ground truth labels.
result Sample complexity scales quasilinearly with heuristics and relations found.
Developed Forex trading heuristics with high profit potential.
problem Reduced trade opportunities due to technical indicator values.
method Machine learning simulation of 10 years of Forex data.
result Optimized trade parameters for 118 pips daily profit.
This paper investigates Shampoo's heuristics and decouples preconditioner updates.
problem Improving Shampoo's heuristics for training neural networks.
method Decomposing preconditioner updates, correcting eigenvalues, and adapting eigenbasis computation frequency.
result Principled techniques to remove Shampoo's heuristics and improve training algorithms.
AdamQLR optimizes Adam with K-FAC heuristics, achieving comparable performance to tuned benchmarks.
problem Improving the performance of Adam optimizers with stabilizing heuristics.
method Combining Adam's update directions with K-FAC's heuristics (damping and learning rate selection).
result Untuned AdamQLR can achieve comparable performance to tuned benchmarks.
Paper introduces ML for optimal motion planning in urban traffic.
problem Variations in search efficiency due to dynamic obstacles.
method Introduces machine learning-based heuristic for optimal motion planning considering dynamic obstacles.
result Added performance consistency for real-time implementation.
A new clustering method combines Kalman filtering with K-Means for better results.
problem Improving clustering efficiency and accuracy in data mining.
method Proposes a new clustering algorithm (HKA-K) that integrates Kalman filtering and K-Means.
result HKA-K outperforms other hybrid meta-heuristic clustering approaches on UCI datasets.
Heuristic tool estimates lactate threshold for easier training decisions.
problem Improving lactate threshold estimation for recreational runners.
method Formalized lactate threshold principles, iterative methodology, heuristic approach.
result Heuristic %60 of 'endurance running speed reserve' is reliable and accessible.
GCOMB learns heuristics for large graphs efficiently.
problem Scalability and practical constraints in graph problem solving.
method GCOMB uses a Graph Convolutional Network (GCN) with Q-learning for efficient heuristic discovery.
result GCOMB is 100 times faster and marginally better than state-of-the-art algorithms.
Improves active learning by dynamically selecting the best acquisition function.
problem Lack of a universally successful acquisition heuristic in active learning.
method Trains an acquisition function as a predictor using reinforcement feedback.
result Always invents a superior acquisition function or adapts to the best heuristic.
Framework for multi-agent RL with human feedback in a Snake game.
problem Improving multi-agent reinforcement learning with human feedback.
method Developed a simulated game environment for offline model training and online competitions. Introduced HILL methods and reward manipulation heuristics.
result Agents with HILL methods outperform those without in online competitions.
Neural LNS improves vehicle routing performance.
problem Optimizing vehicle routes with constraints.
method Integrates deep learning with large neighborhood search.
result Significantly outperforms existing methods on CVRP.
GE finds failures in autonomous systems without domain heuristics.
problem Finding failures in autonomous systems without domain-specific heuristics.
method Adaptive stress testing using go-explore (GE) algorithm.
result GE finds failures in scenarios other RL techniques cannot solve.
Paper tackles flexible bin packing for e-commerce, reducing costs.
problem Optimizing packing of cuboid items into bins with minimal surface area.
method Multi-task Selected Learning approach to generate item packing sequence and orientation.
result Selected Learning method achieves 5.47% cost reduction compared to greedy algorithms.
Rejoinder on slope heuristics for model selection in regression.
problem Model selection in least-squares fixed-design regression with biased models and general noise.
method Proves the slope heuristics works even with significant bias and computes expectations for Gaussian noise.
result The slope heuristics is valid even when models are biased and noise has a general dependence structure.
Neuro# learns heuristics to speed up #SAT solvers.
problem Efficiently solving #SAT problems for large industrial instances.
method Learning branching heuristics to improve #SAT solver performance.
result Neuro# reduces step count and wall-clock time on diverse problem families.
A new Chinese Checkers agent combines heuristics, MCTS, and deep RL.
problem Challenging state-space and unbounded depth in Chinese Checkers.
method Combines heuristics, Monte Carlo Tree Search, and deep reinforcement learning.
result Competent agent reaches human player level.
ResQ uses reinforcement learning to optimize rescue efforts in disaster scenarios.
problem Optimizing emergency response in urban disaster zones.
method Heuristic multi-agent reinforcement learning scheduling algorithm.
result ResQ outperforms state-of-the-art methods in rescue efficiency.
New method combines heuristics and search techniques to speed up cooperative planning for autonomous vehicles.
problem Efficient cooperative planning for autonomous vehicles in complex traffic scenarios.
method Combining learned heuristics with Monte Carlo Tree Search (MCTS) to guide search towards promising actions.
result Better solutions at lower computational costs achieved through accelerated planning.
Deep neural networks approximate solutions to NP-hard problems.
problem Approximating solutions to NP-hard combinatorial optimization problems.
method Homotopic recurrent neural networks combined with reinforcement learning.
result Homotopic RNNs improve the quality of solutions compared to vanilla RNNs.
Dynamic classifier chains improve multi-label classification efficiency.
problem Building efficient multi-label classification models.
method Dynamic ensemble of chain classifiers using Naive Bayes and nearest neighbor approaches, with heuristic for label order optimization.
result The proposed dynamic chain model based on Naive Bayes classifier and heuristic is efficient for multi-label classification.
This research evaluates and introduces new heuristics for clustering Bitcoin blockchain entities.
problem Efficiently analyzing the vast number of Bitcoin blockchain entities.
method Examined and introduced four new heuristics for clustering Bitcoin blockchain entities.
result Introduced clustering ratio to measure heuristic effectiveness.
Bin Packing problems have been widely studied because of their broad applications in different domains. Known as a set of NP-hard problems, they have different vari- ations and many heuristics have been proposed for obtaining approximate solutions. Specifically, for the 1D variable sized bin packing problem, the two ke…
Cross-dimensional neural networks improve AI in Catan game.
problem Challenging to build AI agents for Catan game using RL.
method Introduced cross-dimensional neural networks to handle game complexities.
result RL agent outperforms best heuristic agent in Catan.