New method learns from either positive or negative feedback alone.
problem Limited applicability of existing preference optimization methods in scenarios with only unpaired feedback.
method Decouples learning from positive and negative feedback, using expectation-maximization (EM) to optimize probability of positive outcomes and explicitly incorporate negative examples.
result Stable learning from negative feedback alone demonstrated.
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.
Adaptive sampler improves recommendation for implicit feedback data.
problem Challenges in predicting user preferences from implicit feedback data.
method Noisy-label robust learning for adaptive sampler design.
result Significant improvement in recommendation quality on real-world datasets.
Negative user preference is an important context that is not sufficiently utilized by many existing recommender systems. This context is especially useful in scenarios where the cost of negative items is high for the users. In this work, we describe a new recommender algorithm that explicitly models negative user prefe…
NPO method improves LLM unlearning without catastrophic collapse.
problem Efficiently unlearning undesirable data from LLMs without losing model utility.
method Negative Preference Optimization (NPO) method based on alignment.
result NPO-based methods achieve better unlearning results and maintain model utility.
Given a linearly ordered set I, every surjective map p: A --> I endows the set A with a structure of set of preferences by "replacing" the elements of I with their inverse images via p considered as "balloons" (sets endowed with an equivalence relation), lifting the linear order on A, and "agglutinating" this structure…
Negative momentum accelerates convergence in minimax games but at a suboptimal rate.
problem The convergence rate of negative momentum in minimax games is suboptimal.
method Extending variational inequality formulation, connecting momentum method with Chebyshev polynomials.
result Negative momentum accelerates convergence locally but at a suboptimal rate.
The paper addresses risk sharing and variability measures among agents with general risk preferences.
problem Risk sharing and variability measures among agents with general risk preferences.
method Characterizes Pareto-optimal allocations using Gini deviation, mean-median deviation, and inter-quantile difference as variability measures.
result Optimal allocations are not comonotonic and feature a mixture of pairwise counter-monotonic structures.
We treat a fairly broad class of financial models which includes markets with proportional transaction costs. We consider an investor with cumulative prospect theory preferences and a non-negativity constraint on portfolio wealth. The existence of an optimal strategy is shown in this context in a class of generalized s…
Investigates consumption and investment strategies with preference for liquid assets.
problem Infinite horizon consumption-portfolio problem with liquid and illiquid risky assets.
method Analyzes properties of value function, categorizes solvency regions, and characterizes optimal policy.
result Liquidity preference leads to higher liquid wealth and lower consumption, potentially negative allocation to illiquid asset.
SRPO improves AI alignment with human preferences through self-improvement and task-independent optimization.
problem AI models trained with RLHF lack self-correction mechanisms and struggle with task generalization.
method SRPO formulates the preference learning problem as a min-max objective, optimizing a self-improvement policy and a generative policy in an adversarial fashion, making the solution task-independent.
result SRPO outperforms existing methods, achieving 90% AI Win-Rate on XSum and 56% on Arena-Hard prompts after a single revision.
New RLHF approach mitigates bias in aligning LLMs with human preferences.
problem Algorithmic bias in RLHF leading to preference collapse.
method Preference Matching (PM) RLHF, using PM regularizer and conditional variant.
result 29% to 41% improvement in alignment with human preferences.
Study optimal consumption and investment for investors with Epstein-Zin preferences.
problem Optimal consumption and investment for investors with Epstein-Zin preferences in an incomplete market.
method Variational characterisation and direct method to prove existence of optimal policies.
result Existence and uniqueness of optimal consumption and investment policies.
Optimizes pension mix of PAYGO, EET, and individual savings.
problem Balancing PAYGO, EET, and individual savings in funded pension schemes.
method Solves a Nash equilibrium between pension participants and government, considering age-dependent preferences and optimal asset allocation.
result Identifies critical ages and optimal contribution rates for maximizing overall utility.
Paper tackles entity matching over multi-source data, optimizing alignment and mitigating negative transfer.
problem Learning effective entity matching models over multi-source large-scale data with relaxed assumptions.
method Proposes a Relaxed Multi-source Large-scale Entity-matching (RMLE) problem and Incentive Compatible Pareto Alignment (ICPA) method.
result Optimized cross-source alignments and mitigated negative transfer, improving entity matching accuracy.
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.
Study on MMV in jump-diffusion models resolves MV's non-monotonicity issues.
problem Non-monotonicity and free cash flow stream problems in MV preferences.
method Explicit solution for MMV preferences in jump-diffusion models, proving non-negative potential measures.
result MMV resolves MV's non-monotonicity and free cash flow stream issues.
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.
The paper shows how curated synthetic data can optimize human preferences in generative models.
problem Contamination of web-scale datasets by synthetic data affects future model training.
method Theoretical study of iterated retraining of generative models with curated synthetic data.
result Data curation can be seen as an implicit preference optimization mechanism, maximizing expected reward.
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…
We study dynamic optimal portfolio allocation for monotone mean--variance preferences in a general semimartingale model. Armed with new results in this area we revisit the work of Cui, Li, Wang and Zhu (2012, MAFI) and fully characterize the circumstances under which one can set aside a non-negative cash flow while sim…
We consider the online one-class collaborative filtering (CF) problem that consists of recommending items to users over time in an online fashion based on positive ratings only. This problem arises when users respond only occasionally to a recommendation with a positive rating, and never with a negative one. We study t…
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 most commonly accepted model for investors' preferences is expected utility theory. More recently, other theories have emerged and pose new challenges to mathematics. The present paper treats preferences of cumulative prospect theory (CPT), where an "S-shaped" utility function is considered (i.e. convex up to a cer…
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.
New method detects inconsistencies in AHP matrices using triadic preference reversals.
problem Challenges in assessing consistency in AHP pairwise comparison matrices.
method Triadic preference reversals to detect inconsistencies between pairs of elements.
result 97% accuracy in detecting inconsistencies, significantly surpassing traditional methods.
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.
This paper proposes a new HDP based online review rating regression model named Topic-Sentiment-Preference Regression Analysis (TSPRA). TSPRA combines topics (i.e. product aspects), word sentiment and user preference as regression factors, and is able to perform topic clustering, review rating prediction, sentiment ana…
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.
We develop a tractable model of realization utility that studies the role of reference-dependent S-shaped preferences in a dynamic investment setting with reinvestment. Our model generates both voluntarily realized gains and losses. It makes specific predictions about the volume of gains and losses, the holding periods…
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.
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…