Paper applies Anderson acceleration to speed up reinforcement learning.
problem Speeding up convergence in reinforcement learning.
method Applies Anderson acceleration, a method for accelerating fixed point computation.
result Shows significant speed up of convergence in preliminary experiments.
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.
Quantum computers can speed up machine learning optimization problems.
problem Long computation times and high resource requirements for classical optimization algorithms in machine learning.
method Developed a mathematical model to leverage quantum parallelism for machine learning.
result Quantum machine learning applied to a 3D time-varying image demonstrated significant speedup.
We apply neuromodulation to deep neural networks to improve learning.
problem Static learning parameters in neural networks limit adaptability.
method Evolved neuromodulatory dynamics modify learning parameters over training.
result Evolution found dynamic, location-specific learning strategies.
In this paper, we provide new complexity results for algorithms that learn discrete-variable Bayesian networks from data. Our results apply whenever the learning algorithm uses a scoring criterion that favors the simplest model able to represent the generative distribution exactly. Our results therefore hold whenever t…
Machine learning aids in clinical prediction tasks.
problem Improving accuracy in clinical predictions.
method Introduction to machine learning concepts and algorithms, followed by practical application to clinical datasets.
result Demonstrated the application of machine learning models to clinical prediction problems.
Paper applies NEAT for dynamic credit evaluation using streaming data.
problem Dynamic credit evaluation using streaming data.
method Neuroevolution of Augmenting Topologies (NEAT) with enhancements.
result NEAT effectively handles dynamic credit evaluation with streaming data.
Reinforcement learning optimizes market making decisions.
problem Optimizing market making decisions in cryptocurrency markets.
method Multi-agent reinforcement learning framework with two agents: macro-agent and micro-agent.
result The proposed framework leads to successful trades in the Bitcoin market.
Analyzes learning and applying preconditioners in MCMC for efficiency.
problem Improving efficiency of MCMC algorithms.
method Non-asymptotic analysis of schemes that learn preconditioners.
result Established non-asymptotic guarantees for preconditioned ULA.
This paper explores using neural networks to improve Airbnb search performance.
problem Plateaued gains from gradient boosted decision tree model in search ranking.
method Applied neural networks to improve search performance.
result Shows elements useful in applying neural networks to a real-life product.
This paper applies machine learning techniques to student modeling. It presents a method for discovering high-level student behaviors from a very large set of low-level traces corresponding to problem-solving actions in a learning environment. Basic actions are encoded into sets of domain-dependent attribute-value patt…
New STDP rule for spiking neurons solves discrete action reinforcement learning tasks.
problem Applying standard STDP to discrete action reinforcement learning tasks.
method Feedback-modulated TD-STDP learning rule for spiking neuron networks.
result Feedback modulation improves credit assignment in reinforcement learning.
Cyclical learning rate improves neural machine translation performance.
problem Optimizing learning rate for neural machine translation.
method Applied cyclical learning rate to transformer-based neural networks.
result Cyclical learning rate significantly impacts neural machine translation performance.
We propose an approach to reduce the bias of ridge regression and regularization kernel network. When applied to a single data set the new algorithms have comparable learning performance with the original ones. When applied to incremental learning with block wise streaming data the new algorithms are more efficient due…
In recent years, deep learning methods applying unsupervised learning to train deep layers of neural networks have achieved remarkable results in numerous fields. In the past, many genetic algorithms based methods have been successfully applied to training neural networks. In this paper, we extend previous work and pro…
A new method improves super learner validation efficiency.
problem Improving the efficiency of super learner validation.
method Bootstrap Bias Corrected Cross Validation applied to Super Learning.
result Bootstrap Bias Corrected Cross Validation proved efficient and cost-effective.
We applied machine learning to predict whether a gene is involved in axon regeneration. We extracted 31 features from different databases and trained five machine learning models. Our optimal model, a Random Forest Classifier with 50 submodels, yielded a test score of 85.71%, which is 4.1% higher than the baseline scor…
Horizon is Facebook's open RL platform for large, slow feedback datasets.
problem Training RL models with large, slow feedback datasets.
method End-to-end RL platform with workflows, data preprocessing, distributed training, etc.
result RL models trained with Horizon significantly outperform supervised learning systems.
The paper improves dialogue quality estimation using a novel user satisfaction model.
problem Improving dialogue quality estimation in spoken dialogue systems.
method Proposes a novel user satisfaction estimator based on BiLSTMs and reinforcement learning.
result The novel user satisfaction estimator outperforms previous models in terms of user satisfaction and task success.
New analysis for learning and applying preconditioners in MCMC improves efficiency.
problem Improving efficiency of MCMC algorithms by modifying them with preconditioners.
method Analyzes and compares computational costs of MCMC schemes with and without preconditioners.
result Establishes non-asymptotic guarantees for MCMC algorithms that learn and use preconditioners.
Federated learning improves keyboard suggestions without user data.
problem Improving search suggestion quality without direct user data access.
method Applied federated learning for global-scale model training and deployment.
result Significant quality increases in search suggestions.
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.
Distributed learning is an effective way to analyze big data. In distributed regression, a typical approach is to divide the big data into multiple blocks, apply a base regression algorithm on each of them, and then simply average the output functions learnt from these blocks. Since the average process will decrease th…
Investigates transfer learning in spatial statistics.
problem Applying transfer learning to spatial statistics.
method Simple MLP models for spatial data.
result Potential of transfer learning in spatial statistics.
We explore a framework called boosted Markov networks to combine the learning capacity of boosting and the rich modeling semantics of Markov networks and applying the framework for video-based activity recognition. Importantly, we extend the framework to incorporate hidden variables. We show how the framework can be ap…
Survey of techniques for diagnosing pediatric sleep apnea from inexpensive data.
problem Diagnosing pediatric sleep apnea from limited and variable data.
method Exploratory data analysis using correlation networks, Mapper, SVD; supervised and unsupervised learning techniques.
result Analysis of various learning techniques applied to pediatric sleep apnea data.
Independent component analysis (ICA) has become a standard data analysis technique applied to an array of problems in signal processing and machine learning. This tutorial provides an introduction to ICA based on linear algebra formulating an intuition for ICA from first principles. The goal of this tutorial is to prov…
Multilayered artificial neural networks are becoming a pervasive tool in a host of application fields. At the heart of this deep learning revolution are familiar concepts from applied and computational mathematics; notably, in calculus, approximation theory, optimization and linear algebra. This article provides a very…
Deep learning uses layers of transformations to predict structured data with uncertainty.
problem Predicting structured high-dimensional data efficiently and with uncertainty.
method Applying layers of semi-affine input transformations to find features for probabilistic statistical methods.
result Achieves scalable prediction rules with uncertainty quantification and feature selection.
This chapter reviews statistical tools for reinforcement learning.
problem Applying RL algorithms in healthcare and ride-sharing platforms.
method Statistical inference tools for RL, including hypothesis testing and confidence interval construction.
result Highlighting the value of statistical inference in RL for both communities.
New speech recognition method uses hypergraphs for better label prediction.
problem Missed information in pairwise relationships between speech samples.
method Hypergraph Laplacian based semi-supervised learning methods applied to speech recognition.
result Sensitivity performance measures of hypergraph methods are better than state-of-the-art methods.
Fortuna simplifies uncertainty quantification in deep learning.
problem Improving uncertainty estimates in deep learning models.
method Supports various calibration techniques including conformal prediction and scalable Bayesian inference.
result Simplifies benchmarking and builds robust AI systems.
This paper introduces self-paced task selection to multitask learning, where instances from more closely related tasks are selected in a progression of easier-to-harder tasks, to emulate an effective human education strategy, but applied to multitask machine learning. We develop the mathematical foundation for the appr…
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.
CPR adds entropy maximization to improve continual learning methods.
problem Catastrophic forgetting in continual learning.
method Classifier-Projection Regularization (CPR) adds an entropy maximization term to existing regularization methods.
result CPR improves accuracy and plasticity in continual learning methods.
New AI learns like neurons, generalizing from sparse rewards.
problem Designing AI that learns without explicit instructions and applies that learning to sparse reward scenarios.
method Combining neuroscience principles with computational efficiency, creating the Neurons-in-a-Box architecture.
result The architecture can learn efficiently and generalize across various tasks, including challenging environments.
Logistic LDA applies LDA to non-categorical data.
problem Applying LDA to non-categorical data is challenging.
method Logistic LDA, a discriminative variant of LDA.
result Logistic LDA can learn from unlabeled data.
This thesis applies RL to market making in China's commodity market.
problem Leverage RL for market making in China's commodity market.
method Developed an automatic trading system using RL.
result RL is feasible for market making in China's commodity market.
The paper evaluates machine learning cyber defenses using log data against adversarial attacks.
problem Evaluating the robustness of machine learning cyber defenses against adversarial attacks.
method Developed a testing framework using deep reinforcement learning and adversarial natural language processing.
result Higher dropout levels increase robustness, with 90% dropout probability showing the highest robustness.
The fingerprint classification problem is to sort fingerprints into pre-determined groups, such as arch, loop, and whorl. It was asserted in the literature that minutiae points, which are commonly used for fingerprint matching, are not useful for classification. We show that, to the contrary, near state-of-the-art clas…
New research on limits of transfer learning, proving key selection and dependence requirements.
problem Insufficient theoretical foundation for transfer learning.
method Proved novel results on transfer learning, emphasizing selection of information and dependence between domains.
result Upper bound on improvement possible with transfer learning, highlighting the need for careful selection.
Deep RL applied for Indian stock trading strategies.
problem Designing profitable trading strategies for Indian stock markets.
method Applied deep reinforcement learning to ten Indian stock datasets.
result Models' performance compared and evaluated.
In this project we further investigate the idea of reducing the dimensionality of datasets using a Borel isomorphism with the purpose of subsequently applying supervised learning algorithms, as originally suggested by my supervisor V. Pestov (in 2011 Dagstuhl preprint). Any consistent learning algorithm, for example kN…
Improved stability and generalization for blackbox learned optimizers.
problem Stability and generalization issues in blackbox learned optimizers.
method Investigation using dynamical systems, modifications to optimizer architecture and meta-training procedure.
result Improved stability and generalization of learned optimizers.
Unified view on selective credit assignment for reinforcement learning.
problem Efficient credit assignment in reinforcement learning.
method Unified temporal-difference algorithms with selective weightings.
result New algorithms for backward credit assignment and off-policy learning.
RL applied to TCLs for power consumption control.
problem Optimizing power consumption using TCLs with RL.
method Modelica-based reinforcement learning (Q-learning) for stochastic TCLs.
result Q-learning parameters affect controller performance.
Paper applies NFSP to Mini-RTS, a small RTS game.
problem Applying AI to RTS games due to their multi-agent nature.
method Neural Fictitious Self-Play (NFSP) combined with policy gradient reinforcement learning.
result NFSP can be effectively applied to Mini-RTS and improved with pretraining.
We consider the statistical problem of learning common source of variability in data which are synchronously captured by multiple sensors, and demonstrate that Siamese neural networks can be naturally applied to this problem. This approach is useful in particular in exploratory, data-driven applications, where neither …