Improved fast rates for decision making with forward-KL regularization in contextual bandits.
problem Improving fast rates for decision making with forward-KL regularization in contextual bandits.
method Streamlined analysis of forward-KL-regularized offline CBs, exploiting the pessimism principle and convex-analytical pipeline.
result First ildeO(ε−1) upper bounds in tabular and general function approximation settings. TSC uses HMC and adaptive transport maps to optimize forward KL for variational inference.
problem Variational inference underestimates uncertainty when minimizing reverse KL.
method TSC uses Hamiltonian Monte Carlo and adaptive transport maps to optimize KL(p||q).
result TSC achieves competitive performance in training variational autoencoders on large-scale data.
VISA improves inference efficiency for complex models.
problem Efficient approximate inference in computationally intensive models.
method Sequential sample-average approximations within a trust region.
result VISA achieves comparable accuracy with computational savings.
This work develops a unified framework for RLHF with general f-divergence regularization.
problem Theoretical understanding of general f-divergence regularization in RLHF. method Holistic approach across f-divergence class, two algorithms based on distinct sampling principles. result Provably efficient algorithms with O(logT) regret and O(1/T) sub-optimality gap. 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.
This paper solves the multiple reference model problem in RLHF with exact solutions and sample complexity guarantees.
problem Limitations of single reference models in aligning LLMs with human feedback.
method Integrates multiple reference models into RLHF frameworks, addressing theoretical challenges with exact solutions and sample complexity guarantees.
result First exact solution to the multiple reference model problem in reverse KL-regularized RLHF.
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.
TREK uses distillation to help students solve hard problems.
problem Stalled progress on hard prompts when current policy lacks useful reasoning trajectories.
method TREK combines distillation and reinforcement learning to expand student support.
result TREK significantly improves student performance on mathematical reasoning and agentic tasks.
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.
This paper introduces 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.
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.
In this paper, we introduce a new form of amortized variational inference by using the forward KL divergence in a joint-contrastive variational loss. The resulting forward amortized variational inference is a likelihood-free method as its gradient can be sampled without bias and without requiring any evaluation of eith…
A new method combines VI and IS to improve Bayesian inference accuracy.
problem Bayesian inference often underestimates posterior tails, leading to miscalibration and degeneracy.
method Proposes a novel combination of optimization and sampling techniques using the forward KL divergence.
result The method guarantees asymptotic consistency and fast convergence to optimal IS and variational approximations.
A new framework predicts hidden Markov model regimes online.
problem Efficiently identify hidden Markov model regimes in streaming data.
method Develops a predictive-first optimisation framework for streaming HMMs, approximating the full posterior predictive distribution.
result The method provides competitive prequential performance compared to Online EM and Sequential Monte Carlo.
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.
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.
New method improves variational inference for better posterior approximation.
problem Challenges in minimizing inclusive KL divergence for amortized variational inference.
method Likelihood-tempered sequential Monte Carlo samplers to estimate inclusive KL gradient.
result SMC-Wake method fits variational distributions more accurately than existing methods.
New method uses neural networks to efficiently approximate Bayesian inference for complex models.
problem Efficiently approximating Bayesian inference for complex models with varying temperatures.
method Fully amortized neural posterior estimator trained on a single forward pass.
result Achieves competitive posterior approximations across various temperatures and benchmarks.
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.
New method guarantees global convergence in variational inference.
problem Limited convergence to local optima in variational inference.
method Minimizes inclusive KL divergence using neural networks and neural tangent kernel.
result Gradient descent dynamics converge to a unique solution in function space.
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.
Unified theory for semi-implicit variational inference, bridging approximation and optimization.
problem Developing a statistical theory for semi-implicit variational inference.
method Unified theory combining approximation and optimization analyses.
result Unified theory characterizes SIVI's ability to recover target distributions and governs asymptotic behavior.
Improves inference-time alignment for diffusion models without updating weights.
problem Aligning diffusion models without updating weights for high-reward outputs.
method Trust-Region Iterative Twisted Sequential Monte Carlo (TRI-TSMC) for variance reduction and efficiency.
result Improves primary alignment objectives on text generation tasks.
AIR-Net adapts low-rank regularization dynamically for better image completion.
problem Fixed low-rank regularization limits adaptability to different images.
method AIR-Net uses adaptive and implicit regularization parameterized by a dynamic Laplacian matrix.
result AIR-Net enhances implicit regularization and outperforms fixed methods in non-uniform missing data scenarios.
A 6-regular triangulation for hyperbolic plane created.
problem Creating a 6-regular triangulation for hyperbolic plane.
method Constructed a 6-regular geodesic triangulation.
result A 6-regular geodesic triangulation of the hyperbolic plane was successfully created.
Gradient descent implicitly regularizes neural networks by penalizing large loss gradients.
problem How to optimize deep neural networks without explicit regularization.
method Backward error analysis to calculate implicit gradient regularization and demonstrate its effectiveness empirically.
result Implicit gradient regularization biases gradient descent toward flat minima, improving model robustness and test errors.
Choquet regularization improves exploration in RL.
problem Improving exploration in reinforcement learning.
method Introducing Choquet regularizers to measure and manage exploration, reformulating RL problems and deriving explicit solutions.
result Explicit optimal distributions and Choquet regularizers for various exploratory samplers.
The paper explores optimal regularizers for data sources, linking them to star bodies.
problem Understanding optimal regularizers for data sources.
method Investigates optimal regularizers for data distributions using star bodies and dual Brunn-Minkowski theory.
result Identifies optimal regularizers and assesses amenability to convex regularization.
A triangulation of a connected closed surface is called weakly regular if the action of its automorphism group on its vertices is transitive. A triangulation of a connected closed surface is called degree-regular if each of its vertices have the same degree. Clearly, a weakly regular triangulation is degree-regular. In…
In this article, we describe symplectic and complex toric spaces associated to the five regular convex polyhedra. The regular tetrahedron and the cube are rational and simple, the regular octahedron is not simple, the regular dodecahedron is not rational and the regular icosahedron is neither simple nor rational. We re…
The paper studies convergence rates of Tsallis entropic regularization in optimal transport.
problem Optimal transport with regularization.
method Γ-convergence and quantization/shadow arguments.
result Derives convergence rate of Tsallis entropic regularization.
PL Morse theory proves strong regularity in low dimensions.
problem Understanding regular and critical points in PL manifolds.
method Introducing homologically and strongly regular points, presenting criteria, and constructing examples.
result In low dimensions d≤4, homologically regular points are always strongly regular. Study uses property elicitation to understand how fairness regularizers affect optimal decisions.
problem Understanding how fairness regularizers change the optimal decision in predictive algorithms.
method Property elicitation to analyze the relationship between loss, regularization, and optimal decision.
result Necessary and sufficient condition for when a property changes with the addition of a regularizer.
Fiedler regularization uses spectral graph theory to improve neural network performance.
problem Improving neural network performance by penalizing weights based on connectivity.
method Uses the Fiedler value of the neural network's graph as a regularization tool, providing theoretical and computational methods.
result Demonstrates Fiedler regularization's effectiveness in improving neural network performance.
Study on convergence rates for optimal transport with regularization.
problem Convergence analysis of divergence-regularized optimal transport.
method Novel methodology using quantization and martingale couplings.
result Sharp rates for various divergences and transport costs.
We establish continuous maximal regularity results for parabolic differential operators acting on sections of tensor bundles on Riemannian manifolds. As an application, we show that solutions to the Yamabe flow instantaneously regularize and become real analytic in space and time. The regularity result is obtained by i…
Improved optimal regularity for harmonic almost complex structures.
problem Establishing optimal regularity for harmonic almost complex structures.
method Quantitative stratification method and rectifiability of singular strata.
result Optimal regularity theory for energy minimizing harmonic almost complex structures.
Dropout is a simple but effective technique for learning in neural networks and other settings. A sound theoretical understanding of dropout is needed to determine when dropout should be applied and how to use it most effectively. In this paper we continue the exploration of dropout as a regularizer pioneered by Wager,…
Regularization plays an important role in generalization of deep neural networks, which are often prone to overfitting with their numerous parameters. L1 and L2 regularizers are common regularization tools in machine learning with their simplicity and effectiveness. However, we observe that imposing strong L1 or L2 reg…
Study on the regularity of p-Gauss curvature flow near flat interfaces.
problem Regularity of p-Gauss curvature flow near flat interfaces. method Analysis of convex hypersurface near the interface.
result Regularity of the convex hypersurface near the interface.
In this paper, we give a new generalization error bound of Multiple Kernel Learning (MKL) for a general class of regularizations, and discuss what kind of regularization gives a favorable predictive accuracy. Our main target in this paper is dense type regularizations including \ellp-MKL. According to the recent numeri…
In this work we study input gradient regularization of deep neural networks, and demonstrate that such regularization leads to generalization proofs and improved adversarial robustness. The proof of generalization does not overcome the curse of dimensionality, but it is independent of the number of layers in the networ…
Paper optimizes Laplacian regularization for sparse network clustering.
problem Improving spectral clustering in sparse networks.
method Formally determines optimal Laplacian regularization.
result Proper regularization is closely tied to state-of-the-art techniques.
We study the evolution equations for a regularized version of Dirac-geodesics, which are the one-dimensional version of Dirac-harmonic maps. We show that for the regularization being sufficiently large, the evolution equations subconverge to a regularized Dirac-geodesic. In the end, we discuss the limiting process of r…
Entropy-regularized NPG converges linearly with linear function approximation.
problem Analyzing convergence of entropy-regularized NPG with function approximation.
method Established finite-time convergence analyses with entropy regularization and linear function approximation.
result Entropy-regularized NPG achieves linear convergence up to a function approximation error.
Regularized linear regression improves binary classification performance, especially with ridge and ℓ1 regularization.
problem Improving binary classification accuracy with noisy labels.
method Systematic study of regularization strengths on linear classifiers trained on noisy binary classification data.
result Ridge regression consistently improves classification error, while ℓ1 regularization can induce sparsity and ℓ∞ regularization can concentrate weights to two values. New algorithm adds Hessian regularization to improve neural network robustness.
problem Improving neural network robustness against adversarial attacks.
method Proposes an efficient algorithm to train neural networks with Hessian operator-norm regularization.
result Hessian operator-norm regularization increases neural network robustness over input gradient regularization.