Study fairness in bandits, proving fair algorithms have cubic regret.
problem Ensuring fair outcomes in multi-armed bandit problems.
method Introduces fairness definition, proves fair and unfair algorithm bounds, connects fairness to KWIK model.
result Proves cubic regret bound for fair algorithms in classic bandits, and polynomial regret for fair linear contextual bandits.
New RL algorithms learn from context in MDPs with smooth dynamics.
problem Learning in MDPs with varying dynamics based on context.
method Proposes algorithms for CMDPs with smooth context-MDP mappings.
result PAC learning algorithm for linear CMDPs.
Bayesian sequence prediction is a simple technique for predicting future symbols sampled from an unknown measure on infinite sequences over a countable alphabet. While strong bounds on the expected cumulative error are known, there are only limited results on the distribution of this error. We prove tight high-probabil…
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.
Meta-learning improves neural networks by adapting learning algorithms.
problem Conventional AI approaches solve tasks from scratch, but meta-learning aims to improve the learning algorithm.
method Meta-learning adapts a learning algorithm based on multiple learning episodes.
result Meta-learning can tackle deep learning challenges like data and computation bottlenecks.
metric-learn simplifies metric learning in Python.
problem Performing distance metric learning efficiently.
method Unified scikit-learn compatible interface for supervised and weakly-supervised metric learning.
result Unified interface for cross-validation and model selection.
Meta-learning speeds up learning new tasks.
problem Designing and improving machine learning pipelines.
method Observing and learning from different machine learning approaches.
result Learning new tasks much faster than traditional methods.
Survey explores how transfer learning improves deep reinforcement learning.
problem Challenges in reinforcement learning efficiency and effectiveness.
method Categorizes and analyzes transfer learning approaches.
result Transfer learning enhances reinforcement learning performance.
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.
Dropout learning is analyzed as ensemble learning to prevent overfitting.
problem Overfitting in deep learning models.
method Dropout learning ignores some inputs and hidden units with a probability, p, and combines them with the learned network.
result Combining neglected hidden units with the learned network can be seen as ensemble learning.
Optimal learning paths designed for E-learning systems using reinforcement learning.
problem Designing optimal learning paths for E-learning systems.
method Developed a hierarchical skill model and a proficiency level model, applied reinforcement learning to find the optimal learning strategy.
result Demonstrated the effectiveness of the proposed framework via numerical experiments.
New theory improves deep learning performance without statistical assumptions.
problem Improving deep learning performance without statistical assumptions.
method Measure-theoretic theory for machine learning, derived regularization method.
result New regularization method outperforms previous methods in various datasets.
Dex improves reinforcement learning by solving complex environments incrementally.
problem Training reinforcement learning agents for complex, ever-changing environments.
method Incremental learning approach, using optimal weights from simpler environments.
result Incremental learning yields superior performance across multiple Dex environments.
HGAIL learns policies without expert demonstrations.
problem Lack of expert demonstrations in imitation learning.
method Combines hindsight and GAIL to learn policies.
result Comparable performance to current methods, with curriculum learning.
New method uses bi-level optimization to learn useful representations for imitation learning.
problem Learning useful representations for multiple tasks in imitation learning settings.
method Formulates representation learning as a bi-level optimization problem.
result Bi-level optimization framework provides sample complexity benefits for imitation learning.
Tabular Q-Learning with learned state abstractions solves continuous control tasks.
problem Challenging reinforcement learning problems in continuous control.
method Learned state abstraction to transform continuous state-space into discrete.
result Tabular Q-Learning with learned abstractions achieves efficient learning in unseen tasks.
Unsupervised meta-learning speeds up reinforcement learning tasks.
problem Efficiently solving new reinforcement learning tasks.
method Formulating unsupervised meta-reinforcement learning and using mutual information for task proposals.
result Unsupervised meta-reinforcement learning effectively acquires accelerated procedures without manual task design.
Pymc-learn simplifies probabilistic machine learning for non-specialists.
problem Making probabilistic machine learning accessible to non-experts.
method Inspired by scikit-learn, Pymc-learn provides a high-level language for probabilistic models.
result Pymc-learn brings probabilistic machine learning to non-specialists with ease, performance, and flexibility.
Study Whittle index learning algorithms for restless bandits with constant stepsizes.
problem Optimizing decisions in restless multi-armed bandits with constant stepsizes.
method Developed Q-learning algorithms with constant stepsizes for index learning in restless bandits, extending to DQN and function approximations.
result The algorithms learn the Whittle index effectively.
AI learns to learn sequentially without forgetting.
problem Preventing catastrophic forgetting in machine learning models.
method Meta-learning a neuromodulatory activation-gating function to control selective activation in deep neural networks.
result State-of-the-art continual learning performance with 600 classes (9,000 updates).
Paper discusses flaws in traditional RL for lifelong learning.
problem Traditional RL fails to model lifelong learning systems.
method Simplified prototype of lifelong RL system.
result Insights into lifelong RL, showing traditional RL's limitations.
New unsupervised learning technique learns independent kernels for better machine learning tasks.
problem Improving unsupervised representation learning for machine learning tasks.
method Stacking convolutional transforms using alternating proximal minimization scheme.
result DCTL outperforms shallow version CTL on benchmark datasets.
Poisson learning doesn't solve graph semi-supervised learning issues.
problem Global information loss in graph-based semi-supervised learning.
method Poisson learning is Laplace regularization with thresholding.
result Poisson learning cannot overcome the global information loss problem.
Meta-learning helps models learn quickly from few samples.
problem Deep learning requires many samples, which are hard to get.
method Meta-learning optimizes models to adapt quickly to new tasks.
result Meta-learning can improve model efficiency and adaptability.
Paper develops a learning algorithm for relational logistic regression.
problem Learning multi-relational data models.
method Structure learning with Schmidt and Murphy's hierarchical assumption and parameter learning using logistic regression.
result The learning algorithm improves RLR model performance compared to other methods.
New self-imitation learning method improves performance in continuous control tasks.
problem Improving off-policy learning in continuous control tasks.
method Proposes a n-step lower bound to generalize lower-bound Q-learning and introduces a new family of self-imitation learning algorithms.
result n-step lower bound Q-learning achieves a better trade-off between bias and contraction rate, leading to improved performance.
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.
Unified framework explains all types of learning, including brain.
problem Lack of clear explanation for deep learning success.
method Constructing a learning principle that equates all learning to probability estimation.
result Unified understanding of learning across different fields.
A neural network learns to update another neural network's parameters.
problem Learning to update parameters of neural networks efficiently.
method Used a LSTM-based network to learn and apply updates to another neural network's parameters.
result The learned algorithm can update parameters of both layers and generalizes well.
This paper reviews data representation learning from traditional methods to deep learning.
problem Learning the intrinsic structure of data.
method Investigates traditional and deep learning methods.
result Deep learning models have achieved top results in various tasks.
Combines deep learning with active learning for image data.
problem Challenges of active learning with deep learning models.
method Bayesian convolutional neural networks integrated into active learning framework.
result Significant improvement in active learning approaches for image data.
Survey of deep learning in sentiment analysis.
problem Improving sentiment analysis accuracy.
method Overview and survey of deep learning applications.
result Deep learning achieves state-of-the-art sentiment analysis results.
Cyclical learning rates improve DRL performance without manual tuning.
problem Manual hyperparameter tuning in DRL is time-consuming and error-prone.
method Proposes cyclical learning rates for DRL problems.
result Cyclical learning achieves similar or better results than fixed learning rates.
Paper bounds parameter transfer learning performance and applies it to self-taught learning.
problem Transfer learning performance bounds and self-taught learning theory.
method Introduces local stability and transfer learnability, derives a learning bound.
result First theoretical learning bound for self-taught learning.
Unsupervised meta-learning improves learning from small labeled data.
problem Acquiring representations from unlabeled data for effective downstream learning.
method Develops an unsupervised meta-learning method that optimizes for task learning ability from unlabeled data.
result Simple task construction mechanisms, like clustering embeddings, lead to good performance on various downstream tasks.
Paper proposes a neural network for learning crossmodal stimuli.
problem Improving crossmodal processing in dynamic environments.
method Deep neural architecture trained by expectation learning.
result Self-adaptable deep learning model for crossmodal stimuli.
Adaptive meta-learning improves few-shot learning and federated learning performance.
problem Improving few-shot learning and federated learning performance.
method Adaptive gradient-based meta-learning methods integrating online convex optimization and sequential prediction algorithms.
result Improved meta-test-time performance on standard problems in few-shot learning and federated learning.
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.
Theoretical analysis shows PU and NU learning can outperform PN learning under certain conditions.
problem Comparing PU and PN learning without negative data.
method Theoretical analysis based on upper bounds on estimation errors.
result Conditions under which PU and NU learning outperform PN learning are identified and proven.
A new meta-meta classification method tackles few-shot learning tasks.
problem Learning with limited data in small-data settings.
method Designing an ensemble of learners for a large set of problems, then learning how to combine them for a new problem.
result Meta-meta classification outperforms traditional meta-learning and ensembling approaches in one-shot learning tasks.
Private learning can be used to efficiently solve online learning problems.
problem The relationship between differentially private learning and online learning efficiency.
method Derive an efficient black-box reduction from differentially private learning to online learning from expert advice.
result An efficient differentially private learner implies an efficient online learner.
The paper proposes a learning algorithm that improves adaptability and generalization.
problem Improving adaptability and generalization in learning models.
method Learning to meta-learn by meta-finetuning on related tasks before adapting to specific tasks.
result Learning to meta-learn improves adaptability and generalization across various tasks.
Theory vs practice in machine learning, showing practical limitations.
problem Applying machine learning theory to real-world business problems.
method Formalized and compared applied learning and agnostic PAC learning.
result Theoretical learning requires impractically large datasets.
The paper argues all machine learning is supervised, challenging the term 'unsupervised learning'.
problem The categorization of machine learning as supervised vs unsupervised is misleading.
method Analyzes clustering and dimensionality reduction algorithms to argue they are internally supervised.
result All machine learning is internally supervised, challenging the term 'unsupervised learning'.
Deep reinforcement learning combines deep learning with reinforcement learning for complex tasks.
problem Complex tasks with high-dimensional data.
method Combining deep learning architectures (autoencoders, CNN, RNN) with reinforcement learning.
result Successful learning of useful representations for high-dimensional data.
Bayesian meta-learning improves few-shot learning with deep kernels.
problem Few-shot learning with small labeled datasets.
method Bayesian treatment of meta-learning using deep kernels.
result Deep Kernel Transfer (DKT) outperforms state-of-the-art algorithms.
Transfer learning improves algorithm recommendation performance.
problem Improving algorithm recommendation with limited data.
method Train a neural network on meta-datasets, then transfer knowledge to similar datasets.
result Transfer learning enhances meta-learning for algorithm recommendation.
Method learns near-optimal rewards and policies from expert examples.
problem Learning reward and policy from expert demonstrations under unknown dynamics.
method Generative adversarial networks with empowerment-regularized maximum-entropy inverse reinforcement learning.
result Method learns near-optimal rewards and policies that generalize well.