Papers Problem Decomposition
“Problem Decomposition” 태그가 달린 논문 54편 · 필터 해제
SparseLLM: Towards Global Pruning for Pre-trained Language Models
The transformative impact of large language models (LLMs) like LLaMA and GPT on natural language processing is countered by their prohibitive computational demands. Pruning has emerged as a pivotal compression strategy, …
Computational EfficiencyProblem DecompositionDivide-or-Conquer? Which Part Should You Distill Your LLM?
Recent methods have demonstrated that Large Language Models (LLMs) can solve reasoning tasks better when they are encouraged to solve subtasks of the main task first. In this paper we devise a similar strategy that break…
Problem DecompositionClient Orchestration and Cost-Efficient Joint Optimization for NOMA-Enabled Hierarchical Federated Learning
Hierarchical federated learning (HFL) shows great advantages over conventional two-layer federated learning (FL) in reducing network overhead and interaction latency while still retaining the data privacy of distributed …
Federated LearningProblem DecompositionSchedulingSmall Language Models Fine-tuned to Coordinate Larger Language Models improve Complex Reasoning
Large Language Models (LLMs) prompted to generate chain-of-thought (CoT) exhibit impressive reasoning capabilities. Recent attempts at prompt decomposition toward solving complex, multi-step reasoning problems depend on …
Overall - TestProblem DecompositionAdaptive-Solver Framework for Dynamic Strategy Selection in Large Language Model Reasoning
Large Language Models (LLMs) demonstrate impressive ability in handling reasoning tasks. However, unlike humans who can instinctively adapt their problem-solving strategies to the complexity of task, most LLM-based metho…
Computational EfficiencyLanguage ModelingLanguage ModellingLarge Language Model+1LLM Guided Inductive Inference for Solving Compositional Problems
While large language models (LLMs) have demonstrated impressive performance in question-answering tasks, their performance is limited when the questions require knowledge that is not included in the model's training data…
Problem DecompositionQuestion AnsweringData-driven Topology and Parameter Identification in Distribution Systems with limited Measurements
This manuscript presents novel techniques for identifying the switch states, phase identification, and estimation of equipment parameters in multi-phase low voltage electrical grids, which is a major challenge in long-st…
Problem DecompositionTime SeriesFast Matrix Multiplication Without Tears: A Constraint Programming Approach
It is known that the multiplication of an $N \times M$ matrix with an $M \times P$ matrix can be performed using fewer multiplications than what the naive $NMP$ approach suggests. The most famous instance of this is Stra…
Deep Reinforcement LearningProblem DecompositionvalidRolling Horizon based Temporal Decomposition for the Offline Pickup and Delivery Problem with Time Windows
The offline pickup and delivery problem with time windows (PDPTW) is a classical combinatorial optimization problem in the transportation community, which has proven to be very challenging computationally. Due to the com…
Combinatorial OptimizationProblem DecompositionComparison of Model-Free and Model-Based Learning-Informed Planning for PointGoal Navigation
In recent years several learning approaches to point goal navigation in previously unseen environments have been proposed. They vary in the representations of the environments, problem decomposition, and experimental eva…
Deep Reinforcement LearningmodelPointGoal NavigationProblem Decomposition+4Distilling Reasoning Capabilities into Smaller Language Models
Step-by-step reasoning approaches like chain of thought (CoT) have proved to be very effective in inducing reasoning capabilities in large language models. However, the success of the CoT approach is fundamentally tied t…
GSM8KKnowledge DistillationProblem DecompositionStrategyQAHybridization of evolutionary algorithm and deep reinforcement learning for multi-objective orienteering optimization
Multi-objective orienteering problems (MO-OPs) are classical multi-objective routing problems and have received a lot of attention in the past decades. This study seeks to solve MO-OPs through a problem-decomposition fra…
Deep Reinforcement LearningProblem Decompositionreinforcement-learningReinforcement Learning (RL)Incremental Recursive Ranking Grouping for Large Scale Global Optimization
Real-world optimization problems may have a different underlying structure. In black-box optimization, the dependencies between decision variables remain unknown. However, some techniques can discover such interactions a…
global-optimizationProblem DecompositionDistributed Optimization in Distribution Systems with Grid-Forming and Grid-Supporting Inverters
With massive penetrations of active grid-edge technologies, distributed computing and optimization paradigm has gained significant attention to solve distribution-level optimal power flow (OPF) problems. However, the app…
Decision MakingDistributed ComputingDistributed OptimizationProblem DecompositionDecomposition Strategies and Multi-shot ASP Solving for Job-shop Scheduling
The Job-shop Scheduling Problem (JSP) is a well-known and challenging combinatorial optimization problem in which tasks sharing a machine are to be arranged in a sequence such that encompassing jobs can be completed as e…
Combinatorial OptimizationJob Shop SchedulingProblem DecompositionSchedulingDynamic Diagnosis of the Progress and Shortcomings of Student Learning using Machine Learning based on Cognitive, Social, and Emotional Features
Student diversity, like academic background, learning styles, career and life goals, ethnicity, age, social and emotional characteristics, course load and work schedule, offers unique opportunities in education, like lea…
DiagnosticDiversityProblem DecompositionPhysics-Guided Problem Decomposition for Scaling Deep Learning of High-dimensional Eigen-Solvers: The Case of Schrödinger's Equation
Given their ability to effectively learn non-linear mappings and perform fast inference, deep neural networks (NNs) have been proposed as a viable alternative to traditional simulation-driven approaches for solving high-…
Mixture-of-ExpertsProblem DecompositionThe 6-Ds of Creating AI-Enabled Systems
We are entering our tenth year of the current Artificial Intelligence (AI) spring, and, as with previous AI hype cycles, the threat of an AI winter looms. AI winters occurred because of ineffective approaches towards nav…
NavigateProblem DecompositionLearning Reward Machines: A Study in Partially Observable Reinforcement Learning
Reinforcement learning (RL) is a central problem in artificial intelligence. This problem consists of defining artificial agents that can learn optimal behaviour by interacting with an environment -- where the optimal be…
Partially Observable Reinforcement LearningProblem Decompositionreinforcement-learningReinforcement Learning+1DiBB: Distributing Black-Box Optimization
We present a novel framework for Distributing Black-Box Optimization (DiBB). DiBB can encapsulate any Black Box Optimization (BBO) method, making it of particular interest for scaling and distributing modern Evolution St…
Problem DecompositionReinforcement Learning (RL)