A new, computationally friendly formula for a class of risk-averse preferences.
problem Characterizing a class of risk-averse preferences called uniformly weighted divergence preferences.
method Introducing a new formula that characterizes UWDP as the translation-invariant hull of state-independent expected utility.
result UWDP are the translation-invariant hull of state-independent expected utility over L0. SURF steers scalarization weights to uniformly traverse the Pareto front.
problem Non-uniform coverage of the Pareto front when using scalarization weights.
method Geometric analysis and CDF mapping to select weights for uniform coverage.
result SURF converges to uniform Pareto front coverage under provable conditions.
Bayesian optimization agent learns user preferences from pairwise comparisons.
problem Learning user preferences from unknown and infinite choices.
method Sequential Bayesian optimization with pairwise comparisons.
result Optimal agent strategy minimizes remaining system uncertainty.
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.
LLM safety alignment explained as divergence estimation.
problem Aligning large language models to avoid harmful outputs.
method Presented a theoretical framework showing alignment methods as divergence estimators.
result KLDO method improves safety alignment using compliance-refusal datasets.
Extends reinforcement learning alignment to scalar rewards, improving math reasoning.
problem Designing reinforcement learning algorithms for general LLM alignment.
method Introduces f-GRPO and f-HAL, estimating f-divergences between reward-aligned and unaligned distributions.
result Improves math reasoning RLVR tasks and mitigates reward hacking.
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.
Model-free preference under ambiguity defined and applied.
problem Understanding and quantifying ambiguity aversion and prudence.
method Introduces a new model-free definition of ambiguity attitudes and applies it in various contexts.
result New definition of ambiguity prudence equivalent to specific mathematical functions.
Stable and consistent model alignment for language models without assuming human preference models.
problem Lack of statistical consistency in existing alignment methods.
method Relative density ratio optimization between preferred and mixture of preferred and non-preferred data distributions.
result Our approach achieves statistical consistency and stability, providing tighter convergence guarantees.
New methods improve LLM preference optimization by intelligently weighting multiple reference models.
problem Improving LLM preference optimization with multiple reference models.
method Introducing four new weighting strategies for multiple-reference preference optimization.
result All four new weighting strategies outperform current methods on preference accuracy.
This paper provides a non-robust interpretation of the distributionally robust optimization (DRO) problem by relating the distributional uncertainties to the chance probabilities. Our analysis allows a decision-maker to interpret the size of the ambiguity set, which is often lack of business meaning, through the chance…
A minimal model of a market of myopic non-cooperative agents who trade bilaterally with random bids reproduces qualitative features of short-term electric power markets, such as those in California and New England. Each agent knows its own budget and preferences but not those of any other agent. The near-equilibrium pr…
New method reduces Bayesian inference time by optimizing Hamiltonian flows.
problem Efficiently constructing a Bayesian coreset with low inferential error.
method Sparse Hamiltonian flows, involving uniform subsampling and momentum quasi-refreshment steps.
result Exponential compression of the dataset and reduced KL divergence to the target.
Bayesian coresets improved with random sampling and quasi-Newton optimization.
problem Efficiently approximate Bayesian posterior distributions for computationally expensive inference.
method Randomly select a subset of data points, then optimize weights using quasi-Newton method.
result First algorithm with high-probability KL divergence bound on coreset quality.
New method optimizes policies without assuming known link functions between preferences and rewards.
problem Policy alignment with unknown and unrestricted link functions.
method Formulates an f-divergence-constrained reward maximization problem, learning policies directly. result Induces a semiparametric single-index binary choice model for policy alignment.
New algorithm uniformly samples high-dimensional convex bodies efficiently.
problem Uniform sampling of high-dimensional convex bodies.
method Stochastic diffusion perspective to show contraction to the target distribution.
result Achieves state-of-the-art runtime complexity with strong guarantees on output.
We propose to interpret distribution model risk as sensitivity of expected loss to changes in the risk factor distribution, and to measure the distribution model risk of a portfolio by the maximum expected loss over a set of plausible distributions defined in terms of some divergence from an estimated distribution. The…
The paper analyzes insurance contracts under distributional uncertainty using Bregman-Wasserstein divergence.
problem Optimal insurance contracts under distributional ambiguity.
method Utilizes Bregman-Wasserstein ball to characterize ambiguity sets, employs robust optimization.
result Derives optimal indemnity functions in closed form and studies their properties.
The paper justifies time-dependent loss reweighting schemes for flow matching and diffusion models.
problem Theoretical justification for time-dependent loss reweighting schemes in flow matching and diffusion models.
method Clarifies that the loss can depend on both time and state, and shows theoretical justification for time-dependent loss weighting schemes.
result Time-dependent loss weighting schemes are theoretically justified for Generator Matching and Edit Flows.
DRO-REBEL improves LLM alignment by robustly updating models online.
problem Overfitting and drifting of LLMs during RLHF.
method DRO-REBEL uses type-p Wasserstein, KL, and χ2 ambiguity sets for robust online updates. result DRO-REBEL achieves faster convergence and better performance than prior methods.
Distances are fundamental primitives whose choice significantly impacts the performances of algorithms in machine learning and signal processing. However selecting the most appropriate distance for a given task is an endeavor. Instead of testing one by one the entries of an ever-expanding dictionary of {\em ad hoc} dis…
Replacing MSE with f-divergence in diffusion models improves robustness under data contamination.
problem Improving robustness of diffusion models under data contamination.
method Replacing MSE with f-divergence in diffusion models.
result Empirical improvement in performance under data contamination.
On the predual of a von Neumann algebra, we define a differentiable manifold structure and affine connections by embeddings into non-commutative L_p-spaces. Using the geometry of uniformly convex Banach spaces and duality of the L_p and L_q spaces for 1/p+1/q=1, we show that we can introduce the α-divergence, for αin (…
AlphaNet improves supernets training with alpha-divergence.
problem Improving the uncertainty distillation in weight-sharing NAS.
method Proposes alpha-divergence for better uncertainty distillation in supernets.
result Significant improvements in model performance across various FLOPs regimes.
The article recovers tensor fields from partial data using weighted divergent ray transforms.
problem Recovering tensor fields from partial data.
method Weighted divergent ray transforms, unique continuation property of fractional Laplacian, explicit reconstruction formulas.
result Recovery of symmetric m-tensor fields and unique continuation for vector fields and symmetric 2-tensor fields. AI models outperform simple rules in cross-asset futures timing, especially with lower transaction costs.
problem Optimizing cross-asset portfolio weights using traditional forecasting and optimization methods.
method End-to-end AI policies that map market states directly to portfolio weights, trained on CME futures using a differentiable Sharpe ratio loss function.
result Transformer-based AI policies outperform simple rules and equal weighting, trading less and matching or exceeding equal weighting through moderate transaction costs.
Estimates causal effects using neural networks for balancing covariates.
problem Estimating causal effects from observational data.
method Neural Balancing Weights (NBW) using α-divergence for density ratio estimation. result Generalized approach for balancing multidimensional data.
A new method for averaging model predictions using minimum divergence.
problem Improving model averaging methods, especially in small samples.
method Minimum divergence framework for model weight calculation.
result Empirically outperforms standard model averaging methods.
A new method resolves non-identifiability in reward modeling using anchor labels.
problem Non-identifiability in reward modeling from pairwise preferences alone.
method Anchor-guided Variance-aware Reward Modeling (AVRM) framework.
result AVRM resolves non-identifiability and improves reward modeling performance.
Automates debiasing for large language model evaluations through Fisher random walk.
problem Rigorous and scalable evaluation of large language models.
method Semiparametric efficient estimator using Fisher random walk for weighted residual balancing.
result Efficient estimation of contextual preference scores for large language models.
The aggregation of k-ary preferences is a historical and important problem, since it has many real-world applications, such as peer grading, presidential elections and restaurant ranking. Meanwhile, variants of Plackett-Luce model has been applied to aggregate k-ary preferences. However, there are two urgent issues sti…
Unified approach to aggregating models and preferences.
problem Consistent aggregation of models and preferences.
method Formal definition and weighted averaging of models and preferences.
result All rational aggregation rules are weighted averages of highest-ranked models/experts.
The paper sorts big data by revealed preferences, improving consumer and policy decisions.
problem Sorting diverse consumer preferences for big data objects like colleges.
method Endogenous weighting of revealed preferences, considering spillover effects.
result Consistent steady-state solution to counterbalance equilibrium.
In this paper we study the asymptotic behavior of second-order uniformly elliptic operators on weighted Riemannian manifolds. They naturally emerge when studying spectral properties of the Laplace-Beltrami operator on families of manifolds with rapidly oscillating metrics. We appeal to the notion of H-convergence intro…
Unified framework to bridge human and LLM judgments.
problem Systematic discrepancies between human and LLM evaluations.
method Latent human preference score and linear transformations of covariates.
result Higher agreement with human ratings and exposure of systematic gaps.
Variational inference with α-divergences has been widely used in modern probabilistic machine learning. Compared to Kullback-Leibler (KL) divergence, a major advantage of using α-divergences (with positive α values) is their mass-covering property. However, estimating and optimizing α-divergences require to use importa…
New aggregation strategy handles unbounded losses with regret bounds.
problem Online optimization with unbounded loss functions.
method Follow The Regularized Leader (FTRL) with φ-divergence.
result Worst regret bound for unbounded losses with alternative divergences.
This paper solves aggregation of Pareto optimal models by using Bayesian priors and weighted averaging.
problem How to rationally aggregate Pareto optimal models while preserving Pareto efficiency.
method Four logical steps: 1) Bayesian models, 2) Prior as preference ranking, 3) Consistent aggregation, 4) Weighted average of priors.
result All rational/consistent aggregation rules follow a generalized hierarchical Bayesian model.
We speed up marginal inference by ignoring factors that do not significantly contribute to overall accuracy. In order to pick a suitable subset of factors to ignore, we propose three schemes: minimizing the number of model factors under a bound on the KL divergence between pruned and full models; minimizing the KL dive…
Given a length n sample from Rd and a neural network with a fixed architecture with W weights, k neurons, linear threshold activation functions, and binary outputs on each neuron, we study the problem of uniformly sampling from all possible labelings on the sample corresponding to different choices of…
We prove that square integrable holomorphic functions (with respect to a plurisubharmonic weight) can be extended in a square integrable manner from certain singular hypersurfaces (which include uniformly flat, normal crossing divisors) to entire functions in affine space. This provides evidence for a conjecture regard…
Analysis shows preference for Chinese yuan in global trade network.
problem Analyzing the preference of countries to trade in US dollars or Chinese yuan.
method Mathematical analysis of world trade network using Ising spin interactions.
result Majority of countries prefer trading in Chinese yuan due to network structure.
A widely applied diversification paradigm is the naive diversification choice heuristic. It stipulates that an economic agent allocates equal decision weights to given choice alternatives independent of their individual characteristics. This article provides mathematically and economically sound choice theoretic founda…
A common approach for defining a reward function for Multi-objective Reinforcement Learning (MORL) problems is the weighted sum of the multiple objectives. The weights are then treated as design parameters dependent on the expertise (and preference) of the person performing the learning, with the typical result that a …
Gradient descent on normalized networks reveals sparsity preferences.
problem Understanding the inductive bias of gradient descent on normalized neural nets.
method Analysis of gradient descent on weight-normalized smooth homogeneous neural nets, focusing on SWN and EWN.
result EWN causes weights to be updated in a way that prefers asymptotic relative sparsity.
IArxiv sorts daily papers by user preference using LDA.
problem Harder for scientists to stay updated with diverse research.
method LDA on paper corpus to extract topics, user preference learning.
result Sorts papers by user preference on underlying topics.
The paper develops a method to estimate consumer preferences from observed rankings.
problem Estimating consumer preferences from partial ranking information.
method Interpreting observed rankings as pairwise comparisons, modeling latent utility, and correcting for selection bias.
result The method improves recommendation performance, especially for previously unconsumed products.
In rank aggregation (RA), a collection of preferences from different users are summarized into a total order under the assumption of homogeneity of users. Model misspecification in RA arises since the homogeneity assumption fails to be satisfied in the complex real-world situation. Existing robust RAs usually resort to…