Study batch reinforcement learning methods for personalized medical treatments.
problem Batch reinforcement learning for personalized medical treatments.
method Direct policy learning and model-based learning approaches.
result Model-based learning is impossible with finite model classes but feasible with relaxed conditions.
Improves reinforcement learning by using learned dynamics models more effectively.
problem Reducing sample complexity in reinforcement learning.
method Model-based value expansion, controlling for model uncertainty.
result Reduces sample complexity of learning continuous control tasks.
Wasserstein and value-aware loss are shown to be equivalent in model-based RL.
problem Challenges in learning useful models in approximate settings.
method Equivalence between Wasserstein metric and VAML objective.
result Minimizing VAML objective is equivalent to minimizing Wasserstein metric.
PALM learns abstract models for efficient planning and task transfer.
problem Efficiently learning and transferring hierarchical models for planning.
method PALM uses a new formal structure (L-AMDP) to learn independent, modular models at multiple levels of abstraction.
result PALM integrates planning and execution, facilitating rapid learning of abstract models.
This review classifies deep generative models from a graphical modeling perspective.
problem Learning with deep generative models from a graphical modeling perspective.
method Organized from graphical modeling perspective, differentiating model definitions from learning algorithms.
result Different learning algorithms can be applied to the same model.
I2As learn to use model predictions to create flexible plans in reinforcement learning.
problem Improving data efficiency and robustness in reinforcement learning models.
method Imagination-Augmented Agents (I2As) combine model-free and model-based reinforcement learning, learning to interpret model predictions to construct flexible plans.
result I2As outperform baselines in data efficiency, performance, and robustness to model misspecification.
The paper proposes a structure learning model for efficient reinforcement learning.
problem Efficient sample-based decision making in complex environments.
method Temporal Gaussian Mixture Model with structure learning.
result The model discovers the number of states and transition probabilities.
Machine can learn its own bias from related tasks.
problem Machine learning bias through hand-crafted features.
method Introduces two models: PAC-based and hierarchical Bayes.
result Machine can learn bias from multiple tasks.
Examines learning efficiency in neural networks and related models.
problem Analyzing efficiency in deep learning models with singular learning coefficients.
method Examined learning coefficients in neural networks and three-layer neural networks with ReLU units.
result Extended results to include Softmax function, providing a broader understanding of learning efficiency.
Probabilistic ML improves healthcare data analysis.
problem Insufficient understanding and incomplete data in healthcare.
method Examination of probabilistic machine learning models for healthcare challenges.
result Probabilistic models enhance healthcare data analysis and model building.
Transfer learning boosts deep learning in source code modeling.
problem Deep learning models are problem-specific and data-hungry.
method Transfer learning to improve performance of deep learning models.
result The proposed approach outperforms state-of-the-art models in source code suggestion task.
Machine learning models adapt to motor learning but face challenges.
problem Adapting machine learning to handle motor variability and differentiate new movements from known ones.
method Parameter adaptation, transfer and meta-learning, reinforcement learning.
result Challenges in applying machine learning models for motor learning support systems.
Meta-learning adapts models for unseen tasks across AI, robotics, and NLP.
problem Adapting models to unseen tasks efficiently and accurately.
method Black-box, metric-based, layered, and Bayesian approaches.
result Meta-learning enhances model generalization and adaptation to unseen tasks.
New deep learning model interprets tabular data with variable selection and explainability.
problem Deep learning models lack interpretability and variable selection.
method Proposes a new network architecture that combines deep learning with generalized linear models.
result The model provides superior predictive power and interpretable results.
GEN Model uses genetic-evolutionary strategy for deep learning.
problem Deep learning models are complex and hard to interpret.
method GEN Model builds a group of unit models through genetic-evolutionary learning.
result GEN Model outperforms state-of-the-art methods in effectiveness and efficiency.
Three approaches for personalized models in machine learning.
problem Training a single model for all users is not optimal in many scenarios.
method User clustering, data interpolation, and model interpolation.
result Learning-theoretic guarantees and efficient algorithms for personalized models.
Survey of integrating planning and learning in model-based reinforcement learning.
problem Sequential decision making in AI, formalized as MDP optimization.
method Systematic coverage of dynamics model learning and planning-learning integration.
result Broad conceptual overview of model-based reinforcement learning.
LC-FL uses generative models to reduce communication costs in federated learning.
problem High communication costs and strict model homogeneity in federated learning.
method LC-FL employs generative models to transmit data and aggregate models.
result LC-FL reduces communication costs and supports heterogeneous models.
Auto-Ensemble automates deep learning model ensembling with adaptive learning rate scheduling.
problem Difficulty in collecting diverse and accurate deep learning models through single training.
method Auto-Ensemble collects model checkpoints and uses adaptive learning rate scheduling to ensemble them.
result Ensembled models converge to various local optima, improving performance on few-shot learning.
Paper develops a method for rapid online learning of deep models.
problem Rapid adaptation of deep models to changing tasks.
method Uses meta-learning to train a model that can adapt to new tasks and recall old ones.
result Meta-learning enables effective continuous adaptation in non-stationary task distributions.
Regularizes model-based planning using energy-based models for efficient learning.
problem Challenges in using learned dynamics models for accurate planning.
method Regularization using energy estimates of state transitions.
result Proposes effective regularization method for planning with pre-trained dynamics models.
Study shows cliff-learning in transfer learning from foundation models.
problem Data-scaling of transfer learning from foundation models in low data regimes.
method Investigation of cliff-learning phenomenon through foundation-model analysis and toy models.
result Cliff-learning reflects compatibility between priors and tasks.
A new model of learning corrects for chance to improve learning outcomes.
problem The importance of chance-corrected measures in learning.
method Developed two models: Informatron and AdaBook, based on empirical psychological results.
result Chance correction facilitates learning, as shown by computational results.
Extends batch active learning to non-differentiable models.
problem Efficiently training machine learning models on large, initially unlabelled datasets.
method Black-box batch active learning for regression tasks that relies solely on model predictions.
result Achieves strong performance on regression datasets compared to white-box approaches for deep learning models.
New deep learning model tackles graph data learning challenges.
problem Handling graph structured data challenges in deep learning models.
method Introduces a deep loopy neural network with extensive connections and a new learning algorithm based on spanning trees.
result Demonstrates effectiveness on real-world graph datasets.
Deep reinforcement learning finds optimal learning policies for adaptive systems.
problem Finding individualized learning plans for learners with unknown latent traits.
method Formulated as a Markov decision process, applied deep Q-learning with a transition model estimator.
result The algorithm efficiently discovers optimal learning policies with small data sets.
Diffusion models learn balanced data representations, unlike classification models.
problem Understanding feature learning in diffusion models.
method Proposed a feature learning framework to analyze diffusion models' training dynamics.
result Diffusion models encourage learning balanced and comprehensive representations.
Relational logistic regression (RLR) is a representation of conditional probability in terms of weighted formulae for modelling multi-relational data. In this paper, we develop a learning algorithm for RLR models. Learning an RLR model from data consists of two steps: 1- learning the set of formulae to be used in the m…
Deep RL solves complex macroeconomic models.
problem Solving dynamic stochastic general equilibrium models with bounded rationality.
method Using deep reinforcement learning to model agents as neural networks.
result Artificially intelligent agents can solve models in all policy regimes.
Paper presents a world model that learns invariant causal features using contrastive unsupervised learning.
problem Learning invariant causal features in unsupervised settings.
method Contrastive unsupervised learning with intervention invariant auxiliary task.
result Significantly outperforms state-of-the-art methods on out-of-distribution point navigation tasks.
Researchers study how skills are learned in neural networks using physics principles.
problem Understanding how skills are sequentially learned in neural networks.
method Abstract and simplify the problem using physics principles, proposing three models: Geometry, Resource, and Domino.
result Models reveal insights into neural scaling laws, learning dynamics, and the benefits of modularity.
Self-paced ensemble learning improves audio classification models.
problem Improving performance of individual models in speech and audio classification.
method A self-paced ensemble learning scheme where models learn from each other over several iterations.
result SPEL significantly outperforms baseline ensemble models.
When faced with the problem of learning a model of a high-dimensional environment, a common approach is to limit the model to make only a restricted set of predictions, thereby simplifying the learning problem. These partial models may be directly useful for making decisions or may be combined together to form a more c…
This work explores meta-learning the mean function of Gaussian processes for better model performance.
problem Challenges in fitting Bayesian models on scarce data, especially in extracting prior knowledge.
method Meta-learning the mean function of Gaussian process priors, analyzing and discussing risks and connections to other meta-learning approaches.
result Meta-learning the mean function of Gaussian processes can be useful in the meta-learning setting.
ScheduleFree+ improves large language model training without schedules or learning rates.
problem Scaling up Schedule-Free Learning to large language models.
method Learning-rate-free and schedule-free method for training large language models.
result ScheduleFree+ outperforms SOTA schedules by 31% at 1000 tokens per parameter.
Generative model learns across different spaces using Gromov-Wasserstein distance.
problem Learning specific aspects of a distribution while modifying others.
method Proposes an approach using Gromov-Wasserstein distance to learn across incomparable spaces.
result Demonstrates flexibility in learning target properties across different domains.
Proposes a new learning framework to prevent model selection pitfalls.
problem Model selection issues in machine learning.
method Encourages multiple models to agree on predictions during training.
result Framework significantly outperforms alternatives in practice.
A new multi-step model improves model-based reinforcement learning efficiency.
problem Expensive environmental interaction in reinforcement learning.
method Proposes a multi-step model for predicting action sequences with variable length.
result Multi-step model outperforms one-step model in preliminary tests.
A reinforcement learning method selects the best short-term load forecasting model.
problem Challenges in selecting the best short-term load forecasting model under varying conditions.
method A Q-learning agent learns the optimal policy of selecting the best forecasting model for the next time step.
result The Q-learning algorithm converges fast and improves forecasting accuracy by approximately 50%.
Machine learning creates non-factor covariance matrices for risk models.
problem Creating robust risk models for financial portfolios.
method Developed an explicit algorithm and source code for machine learning risk models.
result Machine learning models outperform traditional risk models in empirical backtests.
This dissertation automates deep learning pipelines and uses meta-learning for better model selection and data augmentation.
problem Challenges in selecting and fine-tuning deep learning pipelines for new datasets.
method Meta-learning for DL pipeline selection and data augmentation, using synthetic data.
result Meta-learned approaches outperform traditional methods in automated DL pipeline selection and data augmentation.
FCL3 learns from multiple representative models to adapt to new tasks.
problem Degradation of performance in lifelong learning models for new task environments.
method Two knowledge libraries: feature learning and model knowledge. Self-selection of representative models for new tasks.
result FCL3 achieves better performance than most lifelong learning frameworks.
Bayesian meta-learning algorithm improves model calibration and accuracy.
problem Improving model calibration and accuracy in few-shot learning.
method Gradient-based variational inference to learn model parameter distributions.
result State-of-the-art calibration and classification results on few-shot benchmarks.
PAC-Net prunes deep models for better transfer learning.
problem Improving transfer learning with over-parameterized models.
method Prune, Allocate, Calibrate (PAC) approach.
result PAC-Net achieves state-of-the-art performance in inductive transfer learning.
This paper compares communication efficiency of split learning and federated learning in various scenarios.
problem Comparing communication efficiency of split learning and federated learning in different settings.
method Examined various practical scenarios of distributed learning setups and compared the two methods.
result Communication efficiency of split learning and federated learning depends on the number of clients, model size, and data samples.
Method learns relational features for Gaifman models from knowledge bases.
problem Structure learning for Gaifman models.
method Relational tree distances to learn relational features.
result Empirical evaluation shows superiority over classical rule-learning.
The paper proposes a method to adapt machine learning models to changing conditions.
problem Machine learning models need to adapt to new conditions in a constantly changing environment.
method Reuse knowledge from existing models to train future generations.
result The proposed method allows machine learning models to adapt and survive in a dynamic environment.
SeCTAR learns latent representations of trajectories for hierarchical reinforcement learning.
problem Learning lower layers in a hierarchy of reinforcement learning problems.
method SeCTAR uses variational autoencoders to learn latent representations of trajectories, combining policy and model consistency.
result SeCTAR effectively solves long-term and multi-stage problems with sparse rewards.