A new policy improvement method using CEM for Actor-Critic.
problem Improving policy efficiency and robustness in reinforcement learning.
method Greedy Actor-Critic (Greedy AC) using Conditional Cross-Entropy Method (CCEM).
result Greedy AC outperforms Soft Actor-Critic and is less sensitive to entropy regularization.
This work enhances collaborative inference privacy by minimizing conditional entropy and boosting robustness against model inversion attacks.
problem Privacy leakage in collaborative inference systems via model inversion attacks.
method Theoretical proof and derivation of a differentiable measure for bounding conditional entropy, followed by a CEM algorithm to maximize it.
result Theoretical proof and experimental validation show that CEM consistently boosts inversion robustness without compromising feature utility or efficiency.
CEM-GD combines CEM and gradient descent for efficient model-based RL.
problem Efficient planning in continuous control settings with large prediction horizons.
method Combines CEM for exploration and gradient descent for exploitation.
result Achieves better performance with fewer samples and less computation time.
Differentiable CEM enables end-to-end learning of non-convex optimization problems.
problem Non-convex optimization of continuous, parameterized objective functions.
method Introducing a differentiable variant of the cross-entropy method (CEM).
result Differentiation of CEM output with respect to parameters enables end-to-end learning.
Introduces Causal Energy Minimization to understand Transformer layers.
problem Empirical parameterization of Transformer blocks remains largely unexplored.
method Causal Energy Minimization framework that recasts Transformer layers as optimization steps on conditional energy functions.
result Identifies design space for Transformer layers including weight sharing and energy-based interpretations.
Hybridizes CEM and gradient descent for efficient model-predictive control.
problem Efficiently planning optimal action sequences in high-dimensional spaces.
method Interleaves Cross-Entropy Method (CEM) and gradient descent steps.
result Faster convergence and avoidance of local optima compared to CEM.
Improved CEM for fast real-time planning in high-dimensional control tasks.
problem Sampling inefficiency of CEM in real-time planning.
method Novel additions to CEM including temporally-correlated actions and memory.
result 2.7-22x less samples and 1.2-10x performance increase.
This paper shows CEM is a special case of TTM, leading to new proofs and improved sample complexity bounds.
problem Improving sample complexity for reinforcement learning algorithms.
method Viewing CEM as an application of TTM, deriving new proofs and bounds.
result Improved sample complexity bounds for CEM under various conditions.
Deep neuroevolution and deep reinforcement learning (deep RL) algorithms are two popular approaches to policy search. The former is widely applicable and rather stable, but suffers from low sample efficiency. By contrast, the latter is more sample efficient, but the most sample efficient variants are also rather unstab…
Enhances data augmentation for regression tasks.
problem Limited effectiveness of data augmentation in regression.
method Curvature-Enhanced Manifold Sampling (CEMS).
result CEMS improves performance in regression tasks.
Combines PCA and CEM for fast clustering and embedding.
problem Dimensionality and slow EM algorithm convergence for clustering.
method Combines PCA and CEM for simultaneous clustering and data embedding.
result Demonstrates improved clustering and embedding performance.
TeLeS improves ASR confidence estimation by considering temporal alignment and lexical errors.
problem Inaccurate confidence scores from E2E ASR models, especially for overconfident predictions.
method Proposes TeLeS, a novel confidence score that considers temporal alignment and lexical errors, and uses shrinkage loss to handle data imbalance.
result TeLeS generalizes well across different languages and ASR models, leading to significant WER reduction.
A new sampler and temperature estimation method enable efficient learning of Boltzmann Machines.
problem Efficient learning of Boltzmann Machines (BMs) is challenging due to high training costs and difficulty in parallelization.
method Proposed a new Boltzmann sampler (Langevin SB, LSB) and an efficient method (Conditional Expectation Matching, CEM) for estimating inverse temperature.
result Established an efficient learning framework (Sampler-Adaptive Learning, SAL) for BMs with greater expressive power than Restricted Boltzmann Machines (RBMs).
New estimator improves off-policy evaluation for large action spaces.
problem Conventional importance-weighting approaches suffer from excessive variance in off-policy evaluation for large discrete action spaces.
method Proposes OffCEM estimator based on conjunct effect model (CEM), applying importance weighting only to action clusters and using model-based reward estimation for residual effects.
result Proposed estimator is unbiased under local correctness condition, providing substantial improvements in OPE especially with many actions.
ACFS optimizes spectral risk under decision-dependent uncertainty using adaptive forest sampling.
problem Minimizing spectral risk with decision-dependent uncertainty.
method ACFS integrates Generalised Random Forests, CEM-guided exploration, rank-weighted augmentation, and multi-start refinement.
result ACFS achieves lowest median oracle spectral risk on both benchmarks.
GACEM optimizes complex multi-modal problems using neural networks.
problem Black-box optimization and constraint satisfaction in multi-modal environments.
method Modified Cross-Entropy Method with masked auto-regressive neural network.
result GACEM outperforms traditional CEM in diverse solutions, mode discovery, and sample efficiency.
A new Bayesian MBRL method improves performance in robotics tasks.
problem Enhancing model-based reinforcement learning with uncertainty.
method Introduces variational inference MPC and probabilistic action ensembles with trajectory sampling (PaETS).
result Consistently improves performance on challenging locomotion tasks.
Unified model explains AT's generative ability.
problem Understanding the generative ability of AT.
method Contrastive Energy-based Models (CEM).
result Improved sample quality in supervised and unsupervised learning.
This paper proposes a method of segmenting temporal data into ordered classes. It is based on mixture models and a discrete latent process, which enables to successively activates the classes. The classification can be performed by maximizing the likelihood via the EM algorithm or by simultaneously optimizing the model…
This paper introduces a novel mixture model-based approach for simultaneous clustering and optimal segmentation of functional data which are curves presenting regime changes. The proposed model consists in a finite mixture of piecewise polynomial regression models. Each piecewise polynomial regression model is associat…
The aim of this research is to introduce a novel structural design process that allows architects and engineers to extend their typical design space horizon and thereby promoting the idea of creativity in structural design. The theoretical base of this work builds on the combination of structural form-finding and state…
Generates samples conditioned on labels using optimal transport.
problem Estimating conditional distributions for specific labels.
method Wasserstein geodesic generator based on optimal transport theory.
result Learned conditional distributions and optimal transport maps.
The paper classifies Finsler surfaces satisfying the T-condition or σT-condition.
problem Characterizing Finsler surfaces based on specific tensor conditions.
method Analyzing Finsler surfaces in dimensions n≥3, proving conditions equivalence, and solving PDEs.
result All Finsler surfaces satisfying the T-condition or σT-condition are classified.
The paper develops a new approach to conditional risk measures using modular convex analysis.
problem Developing a new method for conditional risk measures.
method Random modular approach to conditional certainty equivalents and niveloids in the conditional L∞-space. result Retrieves a conditional variational formula for optimized certainty equivalents and applies it to the conditional entropic risk measure.
Paper constructs solutions to Bogomolny equations with specific boundary and asymptotic conditions.
problem Constructing solutions to Bogomolny equations with given boundary and asymptotic conditions.
method Using generalized Nahm pole boundary condition and real symmetry breaking condition.
result Solutions analogous to instanton solutions, satisfying different asymptotic conditions.
We extend probabilistic programming to handle conditioning on marginal distributions.
problem Conditioning probabilistic programs on marginal distributions of observable variables.
method We define and implement stochastic conditioning, allowing inference in probabilistic programs conditioned on marginal distributions.
result We demonstrate the effectiveness of stochastic conditioning in various real-life scenarios.
New tests for conditional copulas based on decision trees.
problem Testing constancy of conditional dependence structure given conditioning events.
method Data-driven decision trees to maximize differences in conditional Kendall's tau.
result Asymptotic distributions of test statistics under the null hypothesis.
Paper finds necessary condition for logarithmic Minkowski problem in higher dimensions.
problem Logarithmic Minkowski problem in higher dimensions.
method Established a necessary condition through generalization and refinement of previous work.
result Generalizes and refines necessary condition for logarithmic Minkowski problem.
This paper introduces a neural operator for probabilistic conditioning.
problem Probabilistic conditioning of random variables X given Y. method Develops a single operator that maps any joint density to its conditional, approximated by neural operators.
result Neural operators can approximate the conditioning operator to arbitrary accuracy.
CSI method learns conditional distributions by estimating flow equations.
problem Learning conditional distributions in generative models.
method Estimates probability flow equations to transport reference to target distribution.
result Derives explicit expressions for conditional drift and score functions.
New conditional risk measures called conditional generalized quantiles defined and characterized.
problem Developing new risk measures for dynamic risk assessment.
method Propose and characterize conditional generalized quantiles using expected utility model and equivalent conditions.
result Characterized conditional generalized quantiles as well-defined and equivalent to a conditional first order condition.
A new method for learning conditional distributions using ODEs and neural networks.
problem Learning conditional distributions efficiently and accurately.
method Conditional Föllmer Flow, discretized with Euler's method, using nonparametric velocity estimation.
result Effective approximation of target conditional distributions, with convergence results for Wasserstein-2 distance.
Sharp statistical theory for conditional diffusion models.
problem Lack of theoretical foundation for conditional diffusion models.
method Sharp statistical theory with approximation of conditional score function.
result Sample complexity bound that adapts to data distribution smoothness.
An analysis is made of reality conditions within the context of noncommutative geometry. We show that if a covariant derivative satisfies a given left Leibniz rule then a right Leibniz rule is equivalent to the reality condition. We show also that the matrix which determines the reality condition must satisfy the Yang-…
New conditions prevent gaps in optimal control problems.
problem Preventing gaps in optimal control problems with state constraints.
method Developed new sufficient conditions not relying on convexity.
result Derived bounds for the size of the relaxation gap.
We identify conditional parity as a general notion of non-discrimination in machine learning. In fact, several recently proposed notions of non-discrimination, including a few counterfactual notions, are instances of conditional parity. We show that conditional parity is amenable to statistical analysis by studying ran…
We consider families of strongly consistent multivariate conditional risk measures. We show that under strong consistency these families admit a decomposition into a conditional aggregation function and a univariate conditional risk measure as introduced Hoffmann et al. (2016). Further, in analogy to the univariate cas…
Develops a rigorous theory for conditional mean embeddings.
problem Efficient conditioning of probability distributions in RKHSs.
method Mathematical theory for both centred and uncentred covariance operators.
result Significantly weakens conditions for applicability of CMEs.
Proposes a new method for interpreting feature importance and effects in dependent feature models.
problem Challenges in interpreting feature importance when features are dependent and interactions are present.
method Conditional Subgroup Approach
result Conditional PFI and PDP estimates based on this approach often outperform existing methods.
Two conditions on primitive elements are shown to be equivalent.
problem Equivalence of primitive stability and Bowditch's BQ-condition. method Proof of equivalence between two conditions on primitive elements.
result Primitive stability and Bowditch's BQ-condition are equivalent. This paper investigates how policy conditioning affects reinforcement learning stability.
problem Improving stability and generalization of reinforcement learning agents.
method The authors study Jacobian conditioning behavior during policy optimization and propose a conditioning regularization algorithm.
result The proposed conditioning regularization algorithm enhances reinforcement learning agent generalization.
New boundary conditions solve Cauchy problem for Dirac operators on spacetimes.
problem Understanding non-local boundary conditions for Dirac operators on spacetimes.
method Define and analyze a class of Lorentzian boundary conditions that are local in time and non-local in spatial directions.
result Well-posed Cauchy problem for the Dirac operator is established under these conditions.
We extend CS divergence to conditional distributions and show its advantages in time series data and sequential decision making.
problem Quantifying the closeness between conditional distributions.
method Developed and estimated a conditional Cauchy-Schwarz divergence using kernel density estimation.
result Conditional CS divergence outperforms previous methods in time series clustering and sequential decision making.
The Samuelson condition is not satisfied by tangent lines of quadratic curves.
problem Area condition for Lagrangian 2-web
method Show that the Samuelson condition is not satisfied
result The Samuelson condition is not satisfied by tangent lines of quadratic curves.
We describe a Groebner basis of relations among conditional probabilities in a discrete probability space, with any set of conditioned-upon events. They may be specialized to the partially-observed random variable case, the purely conditional case, and other special cases. We also investigate the connection to generali…
A new method tests conditional independence by transforming it into an unconditional problem using transport maps.
problem Testing conditional independence between two random vectors given a third.
method Constructing transport maps to transform conditional independence into unconditional independence, estimating these maps from data using conditional continuous normalizing flow models.
result The proposed method is validated through simulations and real-data analysis, demonstrating practical effectiveness.
Generalizes moment-matching for exponential families with conditioning or hidden data.
problem Generalizing moment-matching conditions for exponential families with conditioning or hidden data.
method First-principles explanation and self-contained derivation of generalized moment-matching conditions.
result Derives generalized moment-matching conditions for conditional exponential families and hidden data.
DG algorithms often fail to generalize well in limited domains, highlighting necessary vs. sufficient conditions.
problem DG algorithms fail to consistently outperform ERM in limited domains.
method Examined necessary and sufficient conditions for DG, proposing a subspace alignment method.
result DG methods focus on sufficient conditions, often neglecting necessary conditions, leading to generalization failures.