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.
Paper proposes using expectation models for planning in stochastic environments.
problem Intractability of learning distribution and sample models in large state and action spaces.
method Proposes using approximate expectation models for MBRL, analyzes linear and non-linear parametrizations, and presents a policy evaluation algorithm.
result Planning with an expectation model is equivalent to planning with a distribution model under certain conditions.
Expected signatures map data streams to lower dimensions, improving ML performance.
problem Leveraging model-free embeddings for domain-agnostic machine learning.
method Expected signatures map data streams to lower dimensions, with convergence results bridging empirical and theoretical estimators.
result A modified expected signature estimator with lower mean squared error for martingale processes.
Proposes data-driven methods for estimating conditional expectations.
problem Estimating conditional expectations when underlying density is unknown.
method Data-driven techniques to directly estimate conditional expectations from training data.
result Extends data-driven method to solve nonlinear equations in stochastic optimization.
This paper compares expected and distributional reinforcement learning methods.
problem Understanding why distributional reinforcement learning performs better than expected reinforcement learning.
method Analyzes differences in tabular, linear, and non-linear approximation settings.
result Distributional RL can hurt performance if it does not induce identical behavior.
We present an objective function for learning with unlabeled data that utilizes auxiliary expectation constraints. We optimize this objective function using a procedure that alternates between information and moment projections. Our method provides an alternate interpretation of the posterior regularization framework (…
Unified algorithm for reinforcement learning with function approximation.
problem Limited scalability of Q(σ,λ) for large-scale learning.
method Proposes GQ(σ,λ) with linear function approximation to extend tabular Q(σ,λ).
result Empirical results show GQ(σ,λ) outperforms full-sampling and pure-expectation methods.
The paper revisits expected signatures in semimartingale models, providing new formulae and simplifying complexity.
problem Computing expected signatures in semimartingale models.
method Revisits and provides new formulae for computing expected signatures in a general semimartingale setting.
result Log-transform of expected signatures simplifies complexity, leading to signature cumulants.
A new method approximates expected empirical loss for stochastic deep learning tasks.
problem Determining optimal step sizes for stochastic gradient descent in deep learning.
method Applying one-dimensional function fitting to noisy losses of vertical cross sections to approximate expected empirical loss.
result The method leads to a robust and straightforward optimization method that performs well across datasets and architectures.
Introduces expected eligibility traces for more efficient credit assignment in reinforcement learning.
problem Efficiently assigning credit to states and actions in reinforcement learning.
method Introduces expected eligibility traces, allowing updates to counterfactual sequences.
result Substantial improvements in temporal-difference learning can be achieved with expected traces.
AI can learn true probabilities if data and assumptions align.
problem Understanding when AI models can accurately represent true objective probabilities.
method Proved conditions under which AI can learn true probabilities.
result Conditions for learning true probabilities are identified.
This paper improves an online learning algorithm using second-order information.
problem Online learning with limited feedback.
method Develops Online Newton Step with Expected Gradient (ONSEG) algorithm.
result Reduces expected regret from O(T^(5/6)) to O(T^(2/3)).
This note shows how to transform high-probability to in-expectation guarantees in machine learning.
problem The challenge of constructing reliable machine learning models due to sampling randomness.
method Transforming high-probability to in-expectation guarantees using a witness condition for unbounded loss functions.
result A technical transformation method for generalization guarantees in machine learning.
Researchers add random metrics to data models to enable operations.
problem Lack of meaningful operations in learned low-dimensional representations.
method Endow latent space of generative models with a random Riemannian metric.
result Derived tight error bounds on expected distances in deterministic approximations.
Paper proposes a probabilistic method to handle missing data in decision trees.
problem Handling missing data in decision trees.
method At deployment time, use density estimators to compute expected predictions. At learning time, fine-tune tree parameters to minimize expected prediction loss.
result Effective compared to baselines in experiments.
Improved deep learning models using new attribution priors and expected gradients.
problem Improving interpretability and performance of deep learning models.
method Introducing new attribution priors and expected gradients method that satisfies interpretability axioms.
result Improves model performance across various real-world tasks.
Paper introduces a new project control method using Monte Carlo and statistical learning.
problem Project control under uncertainty.
method Integrates Earned Value Methodology with Monte Carlo simulation and statistical learning.
result Estimates probabilities of project success and duration.
New methods for estimating nested expectations in machine learning.
problem Nested expectations in machine learning and statistics.
method Investigation and analysis of statistical implications of nesting Monte Carlo estimators.
result Established conditions for convergence of nested MC estimators and derived corresponding rates.
Paper tackles conditional expectation estimation using compactification operators.
problem Estimating conditional expectations from product of two random variables.
method Operator theoretic approach using kernel integral operators in reproducing kernel Hilbert space.
result Solutions allow numerical approximation and convergence of data-driven implementations.
This paper distills Bayesian posterior expectations for deep neural networks.
problem Improving deep neural network performance and uncertainty quantification.
method Develops a framework for distilling expectations from Bayesian posterior distributions using Monte Carlo samples.
result The framework successfully distills posterior predictive distribution and expected entropy.
This paper improves active learning for Gaussian process regression to handle distributional uncertainty.
problem Active learning for Gaussian process regression does not guarantee accurate predictions for target distributions.
method Proposes two methods to reduce worst-case expected error for Gaussian process regression.
result Shows an upper bound of the worst-case expected squared error, suggesting finite data labels can achieve arbitrarily small error.
The article analyzes LCE in Hilbert space, deriving new formulas and regularisation methods.
problem Analyzing conditional expectation in infinite-dimensional Hilbert space.
method Establishing analytical properties and regularisation for LCE in Hilbert space, deriving new formulas.
result Simple derivation and intuitive justification of conditional mean embedding formula.
RUDDER simplifies Q-value estimation for delayed rewards in MDPs.
problem Solving delayed rewards in reinforcement learning with bias and variance issues.
method Reward redistribution and return decomposition to simplify Q-value estimation.
result RUDDER significantly speeds up Q-value estimation and improves performance on Atari games.
New methods improve uncertainty in machine learning predictions for asset returns.
problem Uncertainty in machine learning predictions for asset returns.
method Developed new methods to construct forecast confidence intervals for expected returns from neural networks.
result Neural network forecasts of expected returns have the same asymptotic distribution as classic nonparametric methods, enabling standard error calculation.
One fundamental goal in any learning algorithm is to mitigate its risk for overfitting. Mathematically, this requires that the learning algorithm enjoys a small generalization risk, which is defined either in expectation or in probability. Both types of generalization are commonly used in the literature. For instance, …
GBC methods compute expected utility without needing the model's density.
problem Computing expected utility in complex models.
method Density-free generative method using quantile neural estimator.
result Efficient estimation of expected utility from simulated data.
Transfer learning improves sentiment classification using XR framework.
problem Lack of labeled data for deep learning.
method XR framework applied to transfer learning between related tasks, using expected label proportions.
result Improved performance on aspect-based sentiment classification.
Estimates MLP expected output without sampling, using fewer FLOPs.
problem Estimating expected loss in machine learning efficiently.
method Approximate representations of activations using cumulants and Hermite expansions.
result Estimates expected output with fewer FLOPs than Monte Carlo sampling.
The paper introduces a new framework for off-policy reinforcement learning.
problem Improving off-policy reinforcement learning algorithms.
method Conceptual framework based on conditional importance sampling.
result Theoretical analysis and concrete algorithm investigation.
Proposes a mixture of expert architecture for polyhedral classifiers.
problem Learning polyhedral classifiers with high accuracy.
method Uses an expectation maximization algorithm to learn parameters.
result Generalization bounds are derived and the method performs comparably to state-of-the-art approaches.
MRCs minimize worst-case expected 0-1 loss and provide performance guarantees.
problem Minimizing expected 0-1 loss in classification.
method Minimizes worst-case expected 0-1 loss over uncertainty sets defined by linear constraints.
result Achieves efficient learning and generalization with performance guarantees.
SMC methods approximate intractable Bayesian inference.
problem Approximating intractable Bayesian inference.
method Sequential Monte Carlo (SMC) methods.
result SMC can approximate intractable expectations and normalizing constants.
Proposes deep learning for joint mean and quantile spatio-temporal modeling.
problem Typical spatio-temporal modeling focuses on conditional expectations, ignoring quantiles.
method Multi-output multi-quantile deep learning approach.
result Joint modeling of mean and quantiles improves predictive density and conditional expectation.
New method corrects active learning for distribution shifts and outliers.
problem Conventional active learning methods fail to account for test-time distribution.
method JEPIG, a hybrid of BALD and EPIG, maximizes expected predictive information gain.
result JEPIG outperforms conventional methods in active learning with distribution shifts.
The paper proposes efficient methods to learn VaR and ES using neural networks and Monte Carlo simulations.
problem Learning conditional VaR and ES in non-parametric setups with heavy-tailed financial losses.
method Two-step approach using Rademacher bounds, neural network quantile regression, and least-squares regression.
result Efficient learning schemes for multiple VaRs and ES are developed.
Frank-Wolfe algorithm improves Apprenticeship Learning.
problem Finding a policy similar to an expert in MDPs without explicit rewards.
method Formulating AL as a projection problem on feature expectations polytope, using Frank-Wolfe algorithm.
result Linear convergence rates for AL using Frank-Wolfe method.
Neural clustering learns to group and represent entities.
problem Automated discovery of distributed symbol-like representations for reasoning and interaction.
method Formalizes the problem as spatial mixture model with neural network parameters, derives differentiable Expectation Maximization clustering method.
result Successfully learns to group and represent individual entities in a sequential perceptual grouping task.
Deep learning improves probabilistic PPDE solution accuracy.
problem Approximating solutions to path-dependent PDEs with limited basis selection.
method Deep learning for conditional expectation estimation with error bounds.
result Deep learning yields more accurate PPDE solutions, especially in high dimensions.
The paper defines and assesses the quality of datasets using a novel expected diameter metric.
problem Lack of rigorous methods to assess data quality.
method Formal definition of data quality, expected diameter metric, Fourier analysis, algebraic methods, probabilistic analysis.
result The expected diameter metric provides theoretical guarantees and practical solutions for data quality assessment.
The paper studies how financial market participants adopt different models of expected returns.
problem Circular situation in financial markets where participants influence each other's opinions.
method Introduces a framework to organize and study multiple expectation models.
result Conditions under which different models are adopted by market participants.
Proposes a method for RL agents to explain their behavior in terms of expected consequences.
problem Difficulty in understanding and trusting RL models.
method Defines state and action descriptions, calculates contrasts, constructs explanation format.
result Human users prefer explanations about policies over single actions.
New method optimizes resource allocation for uncertain tasks.
problem Optimal resource allocation for uncertain tasks with limited capacity.
method Formulated as an assignment problem, optimized using learning to rank with net discounted cumulative gain.
result Achieves higher expected profit and precision compared to classification methods.
Proposes a method to classify with missing features using expected predictions.
problem Challenges of missing feature values in classifier performance.
method Computes expected predictions using geometric programming to learn a naive Bayes distribution.
result Achieves performance similar to full feature classifiers and outperforms imputation techniques.
A new method for fitting mixture models using Boltzmann exploration.
problem Challenges in learning mixture models, especially with good initialisation.
method Boltzmann exploration expectation-maximisation (BEEM) algorithm.
result BEEM can escape local optima and is insensitive to parameter initialisation.
Framework for optimizing search engine rankings using observational data.
problem Optimizing ranking policies for search engines using limited observational data.
method Formulated expected reward optimization problem, estimated context value distribution, trained ranking policy via Bayesian inference.
result Demonstrated trade-offs in ranking policies trained on empirical reward estimates.
Quantum EM algorithm improves clustering for Gaussian mixtures.
problem Improving clustering efficiency for Gaussian mixture models.
method Quantum expectation-maximization algorithm for Gaussian mixture models.
result Quantum EM algorithm demonstrates robustness and speedup.
Paper tackles expected predictions computation for arbitrary generative models.
problem Hard to compute expected predictions for arbitrary generative models.
method Identifies tractable generative and discriminative models for expected predictions.
result Tractable computation of high-order moments and expectations for classification.
This paper makes two contributions to Bayesian machine learning algorithms. Firstly, we propose stochastic natural gradient expectation propagation (SNEP), a novel alternative to expectation propagation (EP), a popular variational inference algorithm. SNEP is a black box variational algorithm, in that it does not requi…