A new method for efficient exploration in reinforcement learning.
problem Improving exploration in reinforcement learning agents.
method State Marginal Matching (SMM) to learn policies matching a target state distribution.
result Agents that optimize SMM explore faster and adapt quicker to new tasks.
We give polynomial-time algorithms for the exact computation of lowest-energy (ground) states, worst margin violators, log partition functions, and marginal edge probabilities in certain binary undirected graphical models. Our approach provides an interesting alternative to the well-known graph cut paradigm in that it …
MWGAN tackles multi-marginal matching problem with Wasserstein GAN.
problem Learning mappings to match a source domain to multiple target domains with cross-domain correlations.
method Develops a novel Multi-marginal Wasserstein GAN (MWGAN) with inner- and inter-domain constraints to minimize Wasserstein distance.
result Theoretical and empirical evaluations show MWGAN's effectiveness on balanced and imbalanced translation tasks.
Generative models learn latent process to match target distributions.
problem Training flow-matching models with auxiliary stochastic dynamics.
method Introduces latent process generator matching, treating generative state as a deterministic image of a Markov process.
result Learn generator of a stochastic process with same marginal distributions.
Study examines time-varying betas and their volatility in bank interest income and expense margins.
problem Understanding the variability of bank betas and their impact on net interest margins.
method Used state-space methods to estimate time-varying betas and conditional volatility.
result Substantial variation in interest income and expense betas, leading to varying net interest margin coefficients.
We propose a framework, named Aggregated Wasserstein, for computing a dissimilarity measure or distance between two Hidden Markov Models with state conditional distributions being Gaussian. For such HMMs, the marginal distribution at any time spot follows a Gaussian mixture distribution, a fact exploited to softly matc…
3MSBM learns smooth trajectories from multiple snapshots.
problem Capturing long-range temporal dependencies in complex systems.
method Lifts dynamics to phase space, generalizes stochastic bridges to multi-marginal conditional problems, learns transport maps preserving intermediate marginals.
result Significantly improves convergence and scalability in capturing complex dynamics.
Unified probabilistic perspective on imitation learning methods using divergence minimization.
problem Understanding and improving imitation learning methods for limited demonstration scenarios.
method Unified probabilistic perspective based on divergence minimization.
result State-marginal matching objective contributes most to IRL's superior performance.
MARGINATTACK improves zero-confidence adversarial attacks' accuracy and efficiency.
problem Improving zero-confidence adversarial attacks' accuracy and efficiency.
method Proposes MARGINATTACK, a zero-confidence attack framework that computes margin with improved accuracy and efficiency.
result MARGINATTACK computes a smaller margin than state-of-the-art zero-confidence attacks and matches state-of-the-art fix-perturbation attacks.
We propose a framework, named Aggregated Wasserstein, for computing a dissimilarity measure or distance between two Hidden Markov Models with state conditional distributions being Gaussian. For such HMMs, the marginal distribution at any time position follows a Gaussian mixture distribution, a fact exploited to softly …
GMC benchmark isolates retrieval in Transformers, revealing max-margin alignment.
problem Understanding how Transformers develop match-and-copy behavior on natural data.
method Introducing Gaussian Match-and-Copy (GMC) as a minimalist benchmark.
result Gradient descent drives parameters to diverge while aligning with max-margin separator.
DTM improves dLLM fine-tuning stability and performance.
problem Intractable sequence-level marginal likelihoods for masked diffusion models.
method Discrete Tilt Matching (DTM) recasts dLLM fine-tuning as state-level matching of local unmasking posteriors under reward tilting.
result DTM yields strong gains on Sudoku and Countdown while remaining competitive on MATH500 and GSM8K.
New algorithm preserves transport maps for better diffusion model training.
problem Training diffusion models with task-specific optimality structures.
method Generalized Schrödinger Bridge Matching (GSBM), inspired by conditional stochastic optimal control.
result GSBM better preserves transport maps, enabling stable convergence and improved scalability.
New margin bound improves generalization for voting classifiers.
problem Improving generalization bounds for voting classifiers.
method Established a new margin-based generalization bound.
result Derives an optimal weak-to-strong learner with matching theoretical lower bound.
Generative models often fail to preserve joint structure despite matching marginals.
problem Generative models fail to capture complex dependencies beyond univariate marginals.
method Introduced D_Sigma(P,Q) = ||Sigma_P - Sigma_Q||_F to measure covariance-level dependence fidelity.
result Covariance-level divergence can lead to structural instability in downstream inference.
New method learns flows between multiple distributions efficiently.
problem Learning dynamic transport maps between multiple empirical distributions.
method Combining flow matching and dynamic optimal transport with potential terms.
result OTP-FM achieves state-of-the-art performance on various datasets.
New lower bounds nearly match existing upper bounds for boosted classifiers.
problem Understanding the generalization performance of boosted classifiers.
method Margin-based lower bounds on boosted classifiers.
result Lower bounds nearly match the kth margin bound, settling the generalization performance of boosted classifiers. Signed-permutation coordinate transport improves model alignment across checkpoints.
problem Improper alignment of coordinate-indexed objects across model checkpoints.
method Introduces sign-marginalized Hungarian matching and coordinate-preserving transport.
result Recovering signed-permutation gauge improves coordinate alignment and model performance.
GDT improves reinforcement learning by matching future state information efficiently.
problem Efficient learning of multi-task policies from trajectory data.
method Generalized Decision Transformer (GDT) for offline hindsight information matching.
result GDT enables effective offline multi-task state-marginal matching and imitation learning.
A new method for learning policies from demonstrations without reinforcement.
problem Learning policies from demonstrations without access to reinforcement signals.
method Energy-based distribution matching (EDM) to learn policy parameters and state marginals.
result EDM yields consistent performance gains over existing algorithms for strictly batch imitation learning.
MSBM extends SB for multi-marginal trajectory inference.
problem Trajectory inference from multiple discrete snapshots.
method Multi-Marginal Schrödinger Bridge Matching (MSBM) using iterative Markovian fitting (IMF).
result MSBM effectively captures complex trajectories and respects intermediate distributions.
EnFF uses flows to speed up DA in high dimensions.
problem Efficiently assimilating noisy data in high-dimensional systems.
method Flow Matching (FM) for training-free, scalable data assimilation.
result EnFF accelerates DA with improved cost-accuracy tradeoffs and scalability.
New algorithms for privately learning decision lists and halfspaces.
problem Private learning of decision lists and halfspaces.
method Differentially private algorithms for PAC and online models.
result Private algorithms match or surpass non-private guarantees.
ScoreMatchingRiesz improves debiased machine learning and policy effects estimation.
problem Improving debiased machine learning and policy effects estimation.
method Score matching and Riesz representer estimation.
result Estimates policy path for continuous treatments, improving interpretability.
The paper improves SVM margin-based generalization bounds.
problem Improving generalization bounds for SVMs.
method Revisiting and improving classic generalization bounds in terms of margins, complementing with a nearly matching lower bound.
result Almost settles the generalization performance of SVMs in terms of margins.
SOAD model improves data assimilation for nonlinear systems.
problem Challenges in classical data assimilation with high nonlinearity.
method State-Observation Augmented Diffusion (SOAD) model for data-driven assimilation.
result SOAD model matches true posterior distribution under mild assumptions.
Improves EM algorithm for better local optima in mixture models.
problem EM algorithm's sensitivity to initialization and bad local optima.
method Big Learning principle applied to upgrade EM algorithm.
result BigLearn-EM delivers optimal solution with high probability.
Bayesian method matches uncertainty to adapt across domains.
problem Label distribution shift across domains degrades model performance.
method Bayesian neural network quantifies uncertainty; joint feature and label distribution matching.
result Improves model performance on domain adaptation tasks.
New method calibrates deep neural network predictions for better uncertainty quantification.
problem Uncertainty quantification for deep neural network predictions.
method Conditional Gaussian prior, copula process, non-parametric marginal distribution.
result Marginally-calibrated predictions from distributional DNN regression.
Score matching errors are not sufficient for measuring diffusion model quality.
problem The L2 score matching error is not a reliable measure of diffusion model performance. method Decomposed score errors into gradient and solenoidal components and analyzed their geometric properties.
result Only the gradient component of the score error affects the marginal distributional quality.
Flow matching improves synthetic data generation for tabular data.
problem Generating synthetic tabular data while preserving privacy.
method Flow matching (FM) and Variational FM for tabular data synthesis.
result FM outperforms diffusion baselines in tabular data synthesis.
A new sampler for FLMs improves token-level decoding controls.
problem Sampling from FLMs using standard methods collapses marginals and produces invalid sequences.
method Samples clean one-hot endpoints from FLM token marginals and uses Ornstein-Uhlenbeck bridges conditioned on these endpoints.
result The method preserves token-wise posterior-predictive marginals and improves quality-diversity tradeoff.
Improved flow matching using Gaussian processes for better sample quality.
problem Training continuous normalizing flows with reduced variance and flexibility.
method Extending conditional flow matching to streams modeled with Gaussian processes.
result Improved quality of generated samples with moderate computational cost.
A new imputation method estimates missing values by matching observed marginals from masked data.
problem Missing values in data undermine statistical and machine learning analysis.
method Estimates a distribution from masked observations using positive semi-definite kernel density estimation.
result The method yields both single and multiple imputations from the same fitted density, with statistical consistency and fast adaptive excess risk.
New findings show score matching's accuracy doesn't ensure numerical stability in diffusion sampling.
problem Numerical stability issues in diffusion sampling despite small forward-marginal error.
method Constructing a smooth score field with arbitrarily small forward-marginal L2 error, showing nonexplosive behavior and moments of every order. result Euler--Maruyama discretizations can converge in probability even when moments diverge, demonstrating failure of weak convergence.
Flow Matching for count data improves sample quality and efficiency.
problem Mapping between count distributions across batches or time points in high-dimensional count data.
method count-FM, a flow-matching framework based on a continuous-time birth-death process with local unit jumps.
result count-FM achieves better sample quality than representative baselines while using fewer parameters.
New geometric analysis shows L2 score error is flawed for diffusion models.
problem Score matching errors in diffusion models do not fully capture distributional quality.
method Decomposed score errors into gradient and solenoidal components, focusing on gradient's role in Fokker-Planck dynamics.
result Only gradient component affects marginal distributional quality; solenoidal component is structurally invisible.
ABI bypasses likelihood intractability with nonparametric distribution matching.
problem Approximate Bayesian computation's inefficiency in high-dimensional settings and under diffuse priors.
method Adaptive Bayesian Inference (ABI) compares posterior distributions directly using nonparametric distribution matching and MSW distance.
result ABI significantly outperforms other methods in high-dimensional or dependent observation regimes.
New method reduces variance in off-policy evaluation for RL.
problem Reducing variance in off-policy evaluation for RL with long horizons.
method Marginalized Importance Sampling (MIS) estimator.
result Achieves mean-squared error bound matching Cramer-Rao lower bound.
New framework using Jensen-Shannon divergence improves domain adaptation theory.
problem Incoherence between empirical domain adversarial training and theoretical H-divergence. method Established new theoretical framework based on Jensen-Shannon divergence, derived bi-directional upper bounds.
result Framework exhibits flexibilities for various transfer learning problems.
Paper proves tight lower bounds for online multicalibration, separating it from marginal calibration.
problem Proving lower bounds for online multicalibration in relation to marginal calibration.
method Information-theoretic approach, constructing group families from orthonormal bases.
result Establishes tight lower bounds for online multicalibration, matching upper bounds up to logarithmic factors.
We address the problem of learning the parameters in graphical models when inference is intractable. A common strategy in this case is to replace the partition function with its Bethe approximation. We show that there exists a regime of empirical marginals where such Bethe learning will fail. By failure we mean that th…
KERMIT models sequences and pairs using a single neural network.
problem Efficient generative modeling for sequences and sequence pairs.
method Insertion-based approach using a single neural network.
result Unified model capable of matching or exceeding state-of-the-art performance.
Feature Quantization improves GAN training stability.
problem Stability issues in GAN training.
method Feature Quantization (FQ) for the discriminator, embedding true and fake data into a shared discrete space.
result FQ-GAN achieves new state-of-the-art performance on various GAN tasks.
New research shows the maximum ℓ1-margin classifier doesn't adapt to sparse ground truths.
problem Understanding the limitations of the maximum ℓ1-margin classifier in high-dimensional settings.
method Analyzing convergence and prediction error rates of the maximum ℓ1-margin classifier.
result Proves tight upper and lower bounds for prediction error, showing benign overfitting.
Improved exploration in RL with latent state marginalization.
problem Complexity of deep probabilistic models limits their practical use in reinforcement learning.
method Adopting latent variable policies within the MaxEnt framework, with low-cost marginalization of latent states.
result Effective marginalization leads to better exploration and more robust training.
Analyzes large-margin classifiers under high-dimensional data.
problem Selecting the best classifier among various margin-based methods.
method Investigates asymptotic performance of large-margin classifiers under two component mixture models.
result Analytical results closely match with Monte Carlo simulations.
New method improves calibration of neural networks by targeting robust margins and local smoothness.
problem Poor calibration of neural networks, leading to unreliable confidence estimates.
method Intervene on training procedure by targeting robust margins and local smoothness.
result Improved out-of-sample calibration without sacrificing accuracy.