New method trains neural samplers to sample from multi-modal distributions efficiently.
problem Mode-seeking behavior of reverse KL divergence hinders effective sampling from multi-modal target distributions.
method Minimizing reverse diffusive KL divergence along diffusion trajectories of model and target densities.
result Demonstrated enhanced sampling performance across various multi-modal distributions.
SRFE clarifies KL divergences without unifying learning frameworks.
problem Inductive biases of KL divergences and their limitations.
method Introducing SRFE, a log-moment-based functional of the likelihood ratio.
result SRFE recovers KL divergences as limits and reveals a mean-variance tradeoff.
Conditional diffusion models can approximate target distributions well with Gaussian-mixture reverse kernels.
problem Approximating target distributions in conditional diffusion models.
method Using finite Gaussian mixtures with ReLU-network logits as reverse kernels, reducing the problem to static conditional density approximation.
result The resulting neural reverse-kernel class is dense in conditional KL divergence under exact terminal matching.
Paper analyzes sample complexity for offline f f f -divergence-regularized contextual bandits.
problem Lack of tight analyses for sample complexity in offline reinforcement learning.
method Novel pessimism-based analysis for reverse KL divergence, establishing i l d e O ( ε − 1 ) ilde{O}(ε^{-1}) i l d e O ( ε − 1 ) sample complexity. result Achieves i l d e O ( ε − 1 ) ilde{O}(ε^{-1}) i l d e O ( ε − 1 ) sample complexity for reverse KL divergence, surpassing existing bounds. Improved KL divergence estimators for normalizing flows lead to faster convergence and better approximations.
problem Estimating KL divergences for normalizing flows efficiently and accurately.
method Path-gradient estimators for reverse and forward KL divergences.
result Path-gradient estimators lead to faster convergence and better approximation results.
DAIS minimizes symmetrized KL divergence between initial and target distributions.
problem Optimizing over initial distributions in importance sampling.
method Differentiable annealed importance sampling (DAIS) minimizing symmetrized KL divergence.
result DAIS minimizes symmetrized KL divergence between initial and target distributions.
Beta diffusion generates bounded data using multiplicative transitions.
problem Generating data within specific ranges.
method Integrates demasking and denoising with scaled and shifted beta distributions.
result KLUBs are more effective for optimizing beta diffusion compared to negative ELBOs.
Improved analysis for diffusion models reduces KL divergence error dependence on data dimension and discretization step size.
problem Analyze the convergence of diffusion-based generative models under minimal assumptions.
method Model the generation process as a composition of reverse ODE and noising steps, leveraging Wasserstein-type error control and noise addition.
result Achieved a linear dependence on data dimension and improved dependence on discretization step size for KL divergence error.
Accelerates convergence in global non-convex optimization with reversible diffusion.
problem Global non-convex optimization challenges.
method Utilizes reversible diffusion processes with adaptive diffusion coefficients.
result Accelerated convergence with reduced discretization error.
Paper tackles offline RL from mixed datasets with adaptive KL regularizer.
problem Challenges in optimizing RL and BC signals with varying action coverage and multiple action modes.
method Adaptively weighted reverse KL divergence regularizer based on TD3 algorithm.
result Empirically outperforms existing offline RL algorithms in MuJoCo locomotion tasks.
This paper introduces f f f -DPO, a generalized approach to Direct Preference Optimization using diverse divergence constraints.
problem Aligning large language models with human preferences while mitigating safety risks.
method Incorporates diverse divergence constraints to simplify the relationship between reward and optimal policy, eliminating the need for estimating the normalizing constant.
result Optimizes LLMs to align with human preferences more efficiently and under a broader set of divergence constraints.
Paper proposes f-DPG for aligning language models with preferences.
problem Aligning language models with user preferences.
method Uses f-divergence to approximate target distributions and minimizes a forward KL from it using DPG.
result Jensen-Shannon divergence often outperforms forward KL divergence, leading to significant improvements.
Two entropy measures quantify suboptimal portfolio performance.
problem Measuring suboptimality in investment portfolios.
method Relative entropy (KL divergence) calculations.
result Suboptimal portfolios appear better than Kelly portfolios under certain measures.
Unified framework for unlearning in diffusion models using KL divergence and likelihood constraints.
problem Removing undesirable data or concepts while preserving utility of pretrained models.
method Constrained optimization framework based on reverse and forward KL divergences, and likelihood constraints.
result Our KL-constrained approach achieves superior retention-unlearning tradeoffs compared to weight-based baselines.
Unified framework for efficient trans-dimensional Bayesian inference using VI and NFs.
problem Efficient trans-dimensional Bayesian inference with reduced computational cost.
method Variational inference with normalizing flows to train transport proposals.
result Our approach minimizes reverse KL divergence and reduces computational cost.
We consider the nonlinear Kalman filtering problem using Kullback-Leibler (KL) and α α α -divergence measures as optimization criteria. Unlike linear Kalman filters, nonlinear Kalman filters do not have closed form Gaussian posteriors because of a lack of conjugacy due to the nonlinearity in the likelihood. In this paper …
The paper connects tempering and entropic mirror descent for sampling.
problem Sampling from a target distribution with known unnormalized density.
method Establishes the connection between tempering SMC and entropic mirror descent, deriving convergence rates and geometric insights.
result Tempering SMC iterates correspond to entropic mirror descent on the reverse KL divergence, providing new optimization perspectives.
DualVDT improves time-series forecasting with a novel dual reparametrized structure.
problem Time-series forecasting with improved performance and analytical rigor.
method Dual reparametrized variational mechanisms on VAE, latent score based generative model, reverse time stochastic differential equation, variational ancestral sampling, KL divergence reduction.
result Advanced performance in time-series forecasting with reduced KL divergence.
Generalized dual discriminator GANs improve upon traditional GANs by using two discriminators and a flexible loss function.
problem Mode collapse in GANs.
method Introducing dual discriminator α α α -GANs and extending the approach to arbitrary functions. result The approach reduces the optimization problem to a linear combination of an f f f -divergence and a reverse f f f -divergence. We propose in this paper a novel approach to tackle the problem of mode collapse encountered in generative adversarial network (GAN). Our idea is intuitive but proven to be very effective, especially in addressing some key limitations of GAN. In essence, it combines the Kullback-Leibler (KL) and reverse KL divergences …
New bounds close the score matching gap for diffusion models.
problem The difference between sample quality and score matching loss in diffusion models.
method Theoretical analysis of score matching gap, developing tighter bounds for KL divergence, reverse KL divergence, and Wasserstein distance.
result The quality of score approximation impacts closing the score matching gap for low noise scales.
New theory explains GAN's high quality but low diversity.
problem Lack of theoretical justification for non-saturating GAN training.
method Showed non-saturating GAN training approximately minimizes a specific f-divergence.
result Non-saturating GAN training minimizes a particular f-divergence.
This work develops a unified framework for RLHF with general f f f -divergence regularization.
problem Theoretical understanding of general f f f -divergence regularization in RLHF. method Holistic approach across f f f -divergence class, two algorithms based on distinct sampling principles. result Provably efficient algorithms with O ( log T ) O(\log T) O ( log T ) regret and O ( 1 / T ) O(1/T) O ( 1/ T ) sub-optimality gap. A new method uses MCMC-assisted normalizing flows for efficient Bayesian sampling.
problem Sampling from complex posterior distributions in Bayesian statistics.
method Training a normalizing flow using direct KL divergence and MCMC assistance.
result The method improves sampling efficiency for complicated posterior distributions.
We quantify forgetting in post-training models, distinguishing mass and drift.
problem Understanding and preventing forgetting in post-training generative models.
method Developed theoretical results under a two-mode mixture abstraction, formalizing mass and drift forgetting.
result Forgetting can be precisely quantified based on divergence direction, geometric overlap, and training regime.
Develops a method for learning proposals in nested importance samplers.
problem Improving sampling quality in complex distributions.
method Nested Variational Inference (NVI) using forward or reverse KL divergence.
result Optimizing nested objectives leads to improved sample quality.
The paper proves learning-curve monotonicity for maximum likelihood estimators in various parametric settings.
problem Establishing monotonicity guarantees for maximum likelihood estimators.
method Variants of GPT-5.2 Pro were used to derive the results.
result The paper proves monotonicity for maximum likelihood estimators in Gaussian and Gamma variables.
Variational inference improves training of generative flow networks.
problem Training generative flow networks efficiently and accurately.
method Define variational objectives in terms of KL divergences and optimize convex combinations.
result Variational inference methods can reduce the variance of gradients in training generative flow networks.
Flow-based models generate data with improved theoretical guarantees.
problem Theoretical analysis of flow-based generative models.
method Proximal gradient descent in Wasserstein space for JKO flow model.
result KL guarantee of data generation by JKO flow model is O ( ε 2 ) O(\varepsilon^2) O ( ε 2 ) . New methods minimize GFlowNet training divergences for better sampling.
problem Training GFlowNets with KL divergence leads to biased and high-variance estimators.
method Design and implement efficient estimators for four divergence measures.
result Properly minimizing these divergences yields a provably correct and effective training scheme.
New KL-divergence for Gaussian distributions based on Wasserstein geometry.
problem Computing KL-divergence for Gaussian distributions efficiently.
method Introducing WKL-divergence based on Wasserstein geometry.
result WKL-divergence evaluates to squared distance between points for Dirac measures.
New method improves ensemble inference for high-class tasks.
problem High inference costs for ensemble models.
method Proxy-Dirichlet target to minimize reverse KL-divergence.
result Resolves gradient issues for large-scale classification tasks.
We address the problem of imitation learning with multi-modal demonstrations. Instead of attempting to learn all modes, we argue that in many tasks it is sufficient to imitate any one of them. We show that the state-of-the-art methods such as GAIL and behavior cloning, due to their choice of loss function, often incorr…
New divergence measures improve KL approximation.
problem Improving KL divergence approximation without AC condition.
method Introduced α α α -geodesical skew divergence. result Properties of α α α -geodesical skew divergence studied. Unified view of KL-divergence and IPMs via DRE, with new DRM metrics.
problem Unified understanding of KL-divergence and IPMs.
method Unified representation via maximum likelihood density-ratio estimation (DRE).
result Unified form of IPMs and novel DRM metrics.
Estimates KL divergence with fairness considerations for sub-populations.
problem Fairly estimate KL divergence between distributions considering sub-populations.
method Proposes multi-group attribution for KL divergence estimation, derived from multi-calibration.
result Shows multi-group attribution provides better KL divergence estimates conditioned on sub-populations.
Improved bounds for estimating discrete distributions in KL divergence.
problem Estimating discrete distributions in KL divergence with accuracy.
method Used Laplace estimator and established concentration bounds.
result Deviation from mean scales as k / n \sqrt{k}/n k / n for n ≥ k n \ge k n ≥ k . New bounds show diffusion models converge nearly linearly in data dimension.
problem Improving convergence bounds for diffusion models.
method Refined discretization of reverse SDE using stochastic localization.
result Linear convergence in data dimension with logarithmic factors.
New method controls classifier guidance in diffusion models.
problem Improving classifier guidance in diffusion models.
method Cross-entropy control of classifier gradients.
result Effective guidance vectors with mean squared error O ( d ε ) O(d \varepsilon ) O ( d ε ) . Causal KL improves on existing metrics for evaluating causal models.
problem Insufficient discrimination between causal models using edit-distance and KL divergence.
method Introducing Causal KL, an augmented KL divergence that considers causal relationships.
result Causal KL variants effectively distinguish between observationally equivalent models.
This work improves convergence guarantees for unadjusted HMC in KL and Rényi divergences.
problem Understanding convergence properties of unadjusted HMC in divergences like KL and Rényi.
method One-shot couplings to establish regularization and lift convergence bounds.
result Quantitative control of relative density mismatch and warm-start requirements.
The study tightens bounds on binomial probabilities and minimums using KL-divergence.
problem Tightening bounds on binomial probabilities and minimums of i.i.d. Binomials.
method Applied Sanov's theorem to derive upper and lower bounds on binomial tail probabilities and minimums, expressed in terms of KL-divergence.
result High probability upper and lower bounds on the minimum of i.i.d. Binomial random variables, finite sample, asymptotically tight.
Improved KL convergence bounds for score diffusion models without restrictive assumptions.
problem Lack of comprehensive quantitative results for diffusion models, especially in non-regular scores and estimators.
method Score diffusion models with fixed step size from Ornstein-Uhlenbeck and kinetic semigroups, providing explicit and sharp KL convergence bounds.
result Explicit and sharp convergence bounds in KL applicable to any data distribution with finite Fisher information.
Ensemble approaches for uncertainty estimation have recently been applied to the tasks of misclassification detection, out-of-distribution input detection and adversarial attack detection. Prior Networks have been proposed as an approach to efficiently \emph{emulate} an ensemble of models for classification by paramete…
New algorithms achieve logarithmic regret in KL-regularized Markov games.
problem Improving sample efficiency in game-theoretic settings with KL regularization.
method Developed OMG and SOMG algorithms for matrix and Markov games, using best response sampling and superoptimistic bonuses.
result Logarithmic regret in T T T that scales inversely with KL regularization strength β β β . Paper relaxes triangle inequality for KL divergence between Gaussian distributions.
problem KL divergence does not satisfy triangle inequality for Gaussian distributions.
method Investigates relaxed triangle inequality and finds supremum.
result Supremum of KL divergence is found and conditions for attaining it are determined.
Study introduces a variational approach for efficient KL divergence estimation in Dirichlet mixture models.
problem Efficient estimation of KL divergence in Dirichlet mixture models.
method Variational approach for a closed-form solution.
result Superior efficiency and accuracy compared to Monte Carlo methods.
We study the asymptotic consistency properties of α α α -Rényi approximate posteriors, a class of variational Bayesian methods that approximate an intractable Bayesian posterior with a member of a tractable family of distributions, the member chosen to minimize the α α α -Rényi divergence from the true posterior. Unique to o…