Optimizes molecular generation for chemist preferences.
problem Models lack inherent preferences for chemist-desired structures.
method Fine-tuning with Direct Preference Optimization.
result Approach is simple, efficient, and highly effective.
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,657 papers · 148 categories
Trend · papers per month
48 results for “Preference Optimization”
Bayesian optimization learns DM preferences for multi-outcome experiments.
problem Optimizing expensive experiments with unknown utility functions and multiple outcomes.
method Alternates preference learning and Bayesian optimization, using pairwise comparisons.
result Preference exploration strategies improve Bayesian optimization performance.
Bayesian optimization with preference learning identifies preferred solutions in multi-objective problems.
problem Optimizing multiple criteria with decision maker preferences in expensive functions.
method Bayesian optimization with interactive preference learning and active acquisition function.
result Identifies the most preferred solution with reduced interaction cost.
Many real-world engineering problems rely on human preferences to guide their design and optimization. We present PrefOpt, an open source package to simplify sequential optimization tasks that incorporate human preference feedback. Our approach extends an existing latent variable model for binary preferences to allow f…
This paper studies robust forward investment and consumption preferences within a zero-volatility context. Different from previous works, we consider an incomplete financial market model due to general investment portfolio constraints. We provide a new PDE characterization and a novel semi-explicit saddle-point constru…
Optimal hedging framework with variational preferences under convex risk measures.
problem Optimal hedging with variational preferences under convex risk measures.
method Theoretical hedging optimization framework with dual representation of risk measures and utilities.
result Derivation of optimality and indifference pricing conditions.
Direct Density Ratio Optimization aligns LLMs with human preferences without assuming specific models.
problem Statistical inconsistency in aligning LLMs with human preferences.
method Direct Density Ratio Optimization (DDRO) estimates density ratio directly.
result DDRO is statistically consistent, converging to true human preferences as data grows.
This work proves win rate is key to understanding preference learning.
problem Understanding preference learning from generative models.
method Analyzing preference learning methods as win rate optimization or non-WRO.
result Proves win rate is the only evaluation respecting preferences and prevalences.
This paper revisits optimal investment strategies for defined contribution pension schemes using forward preferences.
problem Optimal investment strategies derived from backward models are not time-consistent and sub-optimal in real scenarios.
method Introduces forward preferences and solves optimal investment strategies for defined contribution pension schemes.
result Constructs optimal investment strategies for defined contribution pension schemes using forward preferences.
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.
The aims of this study are twofold. First, we consider an optimal risk allocation problem with non-convex preferences. By establishing an infimal representation for distortion risk measures, we give some necessary and sufficient conditions for the existence of optimal and asymptotic optimal allocations. We will show th…
Study recovers investor preferences from portfolio data using synthetic data and robust optimization.
problem Recovering latent investor preferences from observed portfolio allocations under uncertainty.
method Inverse portfolio optimization framework integrating robust optimization and regret-based inference.
result Accurate recovery of transaction cost parameters and partial identifiability of ESG penalties under preference misspecification and market shocks.
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.
SLHF uses sequential game theory to optimize preferences from human feedback.
problem Optimizing preferences from human feedback in sequential settings.
method SLHF frames the problem as a sequential-move game between Leader and Follower, decomposing the optimization into refinement and adversarial optimization.
result SLHF achieves strong alignment across diverse preference datasets and scales to large models.
Bayesian optimization with preference learning using monotonic neural networks.
problem Optimizing complex systems with multiple conflicting objectives.
method Proposes a neural network ensemble for utility surrogate modeling, leveraging monotonicity.
result Demonstrates superior performance compared to existing methods.
Optimizes crowdsourced preference-based subjective evaluation with online learning.
problem Large-scale evaluation of generative media using crowdsourcing due to combinatorial explosion.
method Automatic optimization of pair combination selections and evaluation volumes with online learning.
result Optimizes evaluation by reducing pair combinations and allocating optimal evaluation volumes.
Improved DPO framework penalizes preference uncertainty to avoid overoptimization.
problem Aligning LLMs to human preferences is challenging due to varied, context-dependent, and ambiguous preferences.
method Developed a pessimistic framework for DPO by introducing preference uncertainty penalization schemes.
result Improved overall performance and better completions on high-uncertainty responses compared to vanilla DPO.
Paper addresses reward hacking in preference optimization, proposing POWER-DL to improve AI alignment.
problem Reward hacking problem in preference optimization, leading to undesired behaviors.
method POWER-DL combines robust reward maximization and dynamic label updates to mitigate reward hacking.
result POWER-DL consistently outperforms state-of-the-art methods on alignment benchmarks.
Introduces SMMV preferences to avoid inconsistency in portfolio selection.
problem Monotone mean-variance preferences fail to differentiate strictly dominant payoffs.
method Introduces strictly monotone mean-variance preferences and applies them to portfolio selection problems.
result SMMV preferences provide a more rational basis for assessing prospects and coincide with MV preferences under certain conditions.
PAC-MOO optimizes constrained multi-objective problems with preferences.
problem Optimizing with constraints and practitioner preferences over objectives.
method Preference-aware constrained multi-objective Bayesian optimization.
result Efficacy demonstrated on real-world analog circuit design problems.
Study on identifying most preferred policy in bandits with vector-valued rewards.
problem Identifying the most preferred policy in bandits with vector-valued rewards.
method Derive a novel lower bound on sample complexity, design the Preference-based Track and Stop (PreTS) algorithm, and derive a new concentration inequality.
result The sample complexity of PreTS is asymptotically tight.
Paper investigates monotonicity issues in AI preference learning.
problem AI models may violate monotonicity when learning preferences.
method Investigates root causes of non-monotonicity in comparison-based preference learning.
result Proves local pairwise monotonicity under mild assumptions.
Training models to prefer certain responses can unintentionally shift probability to harmful ones.
problem Likelihood displacement in DPO models, leading to unintended unalignment.
method Characterized and mitigated likelihood displacement using CHES score.
result Training models to prefer certain responses can unintentionally shift probability mass to harmful responses.
Preference Elicitation and Robust Optimization with Multi-Attribute Quasi-Concave Choice Functionsq-fin.RM
Decision maker's preferences are often captured by some choice functions which are used to rank prospects. In this paper, we consider ambiguity in choice functions over a multi-attribute prospect space. Our main result is a robust preference model where the optimal decision is based on the worst-case choice function fr…
Active learning framework for optimizing human preferences in reinforcement learning.
problem Selecting most informative feedback for training models of human preferences.
method Proposes an active learning framework to collect preferential feedback online or offline.
result Errors in DPO logit estimates diminish with more feedback.
Unified approach to RLHF tackles uncertainty in reward function.
problem Uncertainty in reward function learned from human feedback.
method Value-incentivized preference optimization (VPO) that regularizes the reward function with value function.
result Theoretical and practical guarantees for both online and offline RLHF settings.
MallowsPO enhances LLM fine-tuning with a dispersion index of human preferences.
problem Lack of diversity in human preferences in DPO.
method Developed a dispersion index based on Mallows' theory to characterize preference diversity.
result Demonstrated improved performance in various tasks using the dispersion index.
Algorithm identifies optimal stable matching in uncertain two-sided markets.
problem Sequential learning in two-sided markets with unknown preferences.
method Pure exploration approach with elimination-based algorithms exploiting partial preference information.
result Identification of pervasive stable matching for optimal stable matching identification.
This paper analyzes MORL and proposes efficient algorithms to learn Pareto optimal policies.
problem Understanding and efficiently learning Pareto optimal policies in multi-objective reinforcement learning.
method Systematic analysis of optimization targets, reformulation of Tchebycheff scalarization, online UCB-based algorithm, preference-free framework.
result Identification of Tchebycheff scalarization as a favorable method and efficient algorithms for learning Pareto optimal policies.
Paper tackles combinatorial reinforcement learning with preference feedback.
problem Modeling long-term user engagement in scenarios like recommender systems and online advertising.
method Assumes a contextual MNL preference model with linear mean utilities and approximates item values. Proposes MNL-VQL algorithm.
result Achieves nearly minimax-optimal regret for linear MDPs with preference feedback.
The paper addresses optimal control in modern tontines with bequest preferences, showing a linear investment strategy.
problem Optimal controls and decreasing allocation in modern tontines with bequest preferences.
method Dual approach to solve optimal control problems with power utilities, modeling bequest preferences.
result Investment strategy almost linearly adjusts from 0% to 100% over time.
Study preferences over uncertain time payments, finds growth-optimality better than expected utility theory.
problem Understanding how people make decisions with uncertain timing of payments.
method Normative model of growth-optimality, revisiting experimental evidence on time lotteries.
result Growth-optimality better explains experimental data on time lotteries than expected discounted utility theory.
The paper analyzes investment and consumption strategies under uncertain market conditions.
problem Investment and consumption under drift and volatility uncertainties.
method Randomization approach to construct robust preferences and strategies.
result Developed optimal and robust investment and consumption strategies remain valid in the physical market.
Optimal insurance and investment strategy under exponential preferences in a correlated market model.
problem Optimal investment and reinsurance strategy for an insurance company under exponential preferences.
method Stochastic control techniques to construct a forward dynamic exponential utility and characterize the optimal strategy.
result Characterization of the optimal investment and reinsurance strategy in a correlated market model.
SPPO optimizes language model alignment by treating preferences as a game and achieving state-of-the-art performance.
problem Capturing intransitivity and irrationality in human preferences for accurate language model alignment.
method Self-play-based approach to identify Nash equilibrium policy through iterative policy updates.
result SPPO achieves state-of-the-art win-rate of 28.53% on AlpacaEval 2.0 without external supervision.
We consider black-box global optimization of time-consuming-to-evaluate functions on behalf of a decision-maker (DM) whose preferences must be learned. Each feasible design is associated with a time-consuming-to-evaluate vector of attributes and each vector of attributes is assigned a utility by the DM's utility functi…
The paper proposes a method to learn and leverage contextual preference distributions for better decision-making.
problem Heterogeneous and context-dependent human preferences in decision-making problems.
method A sequential learning-and-optimization pipeline using a bounded-variance score function gradient estimator to train a predictive model mapping contextual features to preference distributions.
result The approach reduces average post-decision surprise by up to 25 times compared to risk-averse baselines in a ridesharing environment.
Paper uses inverse optimization to measure risk preference from investment portfolios.
problem Measuring subjective risk preference in investment portfolios.
method Inverse optimization on mean-variance framework.
result Quantified risk preference parameters validated with existing measures.
Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizercs.LG
Mitigates overoptimization in RLHF by reformulating SFT loss as a preference optimization loss.
problem Overoptimization in RLHF where reward model misguides generative model.
method Proposes a theoretical algorithm that minimizes maximum likelihood estimation and reward penalty, reformulates as simple objective combining preference optimization and supervised learning losses.
result Improved performance of RPO compared to DPO baselines in aligning LLMs.
AOT aligns LLMs on distributional preferences via optimal transport.
problem Current LLM alignment techniques lack distributional level alignment.
method Alignment via Optimal Transport (AOT) aligns LLMs on unpaired preference data.
result AOT enables alignment by penalizing reward distribution violations.
Paper analyzes venture capital exit decisions under inconsistent preferences.
problem Time-inconsistent preferences in venture capital exit timing.
method Modeling four types of venture capitalists with varying levels of inconsistency.
result Time-inconsistent venture capitalists exit earlier than consistent ones.
Optimal risk sharing without convex preferences using aggregate convexity.
problem Risk sharing among non-convex preferences.
method Aggregate convexity principles and Lyapunov convexity, combined with approximation arguments for law invariant risk measures.
result Derivation of a computationally tractable formula for the conjugate of the value function.
Inverse reinforcement learning (IRL) enables an agent to learn complex behavior by observing demonstrations from a (near-)optimal policy. The typical assumption is that the learner's goal is to match the teacher's demonstrated behavior. In this paper, we consider the setting where the learner has its own preferences th…
Many real-world applications are characterized by a number of conflicting performance measures. As optimizing in a multi-objective setting leads to a set of non-dominated solutions, a preference function is required for selecting the solution with the appropriate trade-off between the objectives. The question is: how g…
PILAF optimizes reward models from human feedback for better policy alignment.
problem Creating accurate reward models from human feedback for policy optimization.
method Policy-Interpolated Learning for Aligned Feedback (PILAF) that explicitly aligns preference learning with maximizing underlying oracle reward.
result PILAF is optimal from both optimization and statistical perspectives, demonstrating strong performance in RLHF settings.
Bayesian framework learns latent preference archetypes for many-objective optimization.
problem Expanding space of trade-offs and context-dependent human values.
method Dirichlet-process mixture model for latent preference archetypes, hybrid queries for efficient information.
result Mixture-aware Bayesian optimization outperforms standard methods on synthetic and real-world benchmarks.
Novel PO algorithms improve LLM alignment tasks.
problem Evaluating PO algorithms on LLM alignment is costly and noisy.
method Designed a diagnostic suite of MuJoCo tasks and datasets, used evolutionary strategies to discover specialized PO algorithms.
result Proposed MPO algorithms significantly outperform existing PO algorithms in LLM alignment.