Research
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

2457 · May 202619922001200920172026
48 results for Condorcet winner

New algorithm reduces dynamic regret in non-stationary dueling bandits using a weighted Borda score.

problem Designing algorithms with low dynamic regret in non-stationary dueling bandits.
method Introducing a novel weighted Borda score framework to analyze the Condorcet problem and establish improved bounds.
result First optimal and adaptive dynamic regret upper bound of ildeO(ildeL1/3K1/3T2/3) ilde{O}( ilde{L}^{1/3} K^{1/3} T^{2/3} ).

This paper tackles combinatorial pure exploration for dueling bandits, aiming to find the best candidate-position match.

problem Finding the best candidate-position match in a dueling bandit setting.
method The paper adapts combinatorial pure exploration for multi-armed bandits to dueling bandits, considering both Borda winner and Condorcet winner cases. It designs PAC and exact algorithms for Borda winner and a fully polynomial time approximation scheme (FPTAS) for Condorcet winner.
result The paper introduces the first algorithm with polynomial running time per round for identifying the Condorcet winner in CPE-DB.

Improved algorithm for adaptive dueling bandits with near-optimal regret bound.

problem Non-stationary dueling bandits with unknown number of preference changes.
method Elimination-based rescheduling algorithm for adaptive dynamic regret.
result Near-optimal ildeO(SextttCWT) ilde{O}(\sqrt{S^{ exttt{CW}} T}) dynamic regret bound.

Unified framework for best arm identification and dueling bandits regret minimization.

problem Best arm identification and dueling bandits regret minimization.
method Tree-Guided Identify-Then-Exploit (TG-ITE) framework.
result Unified approach achieving optimal sample complexity and regret guarantees.

New algorithm optimizes dueling bandits for both stochastic and adversarial preferences.

problem Optimizing decision-making in environments where only relative preferences are observed.
method Proposed a reduction from dueling bandits to multi-armed bandits, achieving optimal regret bounds.
result First best-of-both-world result for dueling bandits, optimal regret bound for Condorcet-winner benchmark.

Unified framework for ranking-and-selection with multiple correct answers and non-answerable estimates

problem Fixed-precision ranking-and-selection in structured settings with non-unique answers and non-answerable estimates
method Unified framework based on answer-wise acceptance sets, restricted generalized likelihood ratio stopping, and answer-pitfall decomposition
result Unified recipe performs well across a broad range of pure-exploration problems

There is a striking relationship between a three hundred years old Political Science theorem named "Condorcet's jury theorem" (1785), which states that majorities are more likely to choose correctly when individual votes are often correct and independent, and a modern Machine Learning concept called "Strength of Weak L…

2020-02-08abs ↗pdf ↗

Paper explores limits and possibilities of aligning LLMs with human preferences.

problem Aligning LLMs with diverse human preferences to ensure fairness and informed outcomes.
method Analysis of probabilistic representation of human preferences and preservation of diverse preferences.
result LLMs can't fully align with human preferences using reward-based approaches due to Condorcet cycles, but mixed strategies are statistically possible.

RLHF performs well despite violating social choice theory axioms.

problem RLHF's empirical success contradicts social choice theory axioms.
method Showed RLHF satisfies pairwise majority and Condorcet consistency under mild assumptions, and introduced new alignment criteria.
result RLHF satisfies pairwise majority and Condorcet consistency under mild assumptions, explaining its practical success.

New algorithm achieves near-optimal performance in dueling bandit problem.

problem Optimizing decision-making in dueling bandit problems with limited adaptive rounds.
method Developed a batched algorithm that matches the asymptotic regret bounds of sequential algorithms under the Condorcet condition.
result Asymptotic regret of O(K2log2(K))+O(Klog(T))O(K^2\log^2(K)) + O(K\log(T)) in O(log(T))O(\log(T)) rounds.

In this paper, we propose a Double Thompson Sampling (D-TS) algorithm for dueling bandit problems. As indicated by its name, D-TS selects both the first and the second candidates according to Thompson Sampling. Specifically, D-TS maintains a posterior distribution for the preference matrix, and chooses the pair of arms…

2016-04-25abs ↗pdf ↗

A game-theoretic approach to multi-criteria ranking from ordinal data.

problem Ranking objects from ordinal data with multiple criteria.
method Generalizing von Neumann winner to multi-criteria setting using Blackwell's approachability.
result The Blackwell winner can be computed as a convex optimization problem and achieves near-optimal sample complexity.

SIREN protocol corrects optimistic winner's scores in LLM evaluation.

problem Optimistic winner's scores in LLM evaluation due to adaptive benchmarking.
method SIREN protocol that freezes post-search shortlist, separates selection and evaluation, and uses bootstrap for uncertainty quantification.
result SIREN provides valid confidence intervals for procedure-performance curves and deployment conclusions.

Study shows big winner stocks significantly impact passive and active investment strategies.

problem Impact of big winner stocks on passive and active investment strategies.
method Numerical and analytical techniques applied to historical stock price data.
result Concentrated portfolios underperform equally weighted indexes due to missing big winner stocks.

This paper reexamines the profitability of loser, winner and contrarian portfolios in the Chinese stock market using monthly data of all stocks traded on the Shanghai Stock Exchange and Shenzhen Stock Exchange covering the period from January 1997 to December 2012. We find evidence of short-term and long-term contraria…

2015-05-02abs ↗pdf ↗

The paper explores game-theoretic alignment of LLMs with human preferences, finding limitations and conditions.

problem Aligning LLMs with human preferences using game theory.
method Systematic study of payoff choices in a two-player zero-sum game for desirable alignment properties.
result Impossibility of preference matching in game-theoretic LLM alignment under standard assumptions.

Data-driven decision-making often overestimates benefits due to the winner's curse.

problem Accurate policy evaluation in data-driven decision-making.
method Model-based policy evaluation using estimated models from data.
result Model-based methods can produce large, spurious reported benefits even when true effects are zero.

Compact models match or exceed GPT's performance in financial news sentiment analysis.

problem Improving financial sentiment analysis models without large computational costs.
method Fine-tuning non-generative, small-sized models (FinBERT, FinDRoBERTa) on a novel market score database.
result Fine-tuned models outperform GPT-3.5 and GPT-4 in zero-shot learning for financial news sentiment analysis.

Study on tracking preference shifts in dueling bandits problems.

problem Tracking significant preference shifts in dueling bandits problems.
method Analysis of dueling bandits with distribution shifts, focusing on significant shifts (Suk and Kpotufe, 2022).
result Design of adaptive algorithms with O(KildeLT)O(\sqrt{K ilde{L}T}) dynamic regret for certain preference distribution classes.

Stochastic LWTA networks resist adversarial attacks while maintaining accuracy.

problem Adversarial robustness of neural networks.
method Replaced ReLU with stochastic LWTA activations, trained with Variational Bayesian and PGD.
result Stochastic LWTA networks achieve state-of-the-art robustness against adversarial attacks.

aMCL uses annealing to improve hypothesis diversity in ambiguous tasks.

problem Limitations of Winner-takes-all in predicting plausible hypotheses.
method Combines simulated annealing with Multiple Choice Learning (MCL).
result Enhanced exploration of hypothesis space during training.

Multi-armed bandit(MAB) problem is a reinforcement learning framework where an agent tries to maximise her profit by proper selection of actions through absolute feedback for each action. The dueling bandits problem is a variation of MAB problem in which an agent chooses a pair of actions and receives relative feedback…

2019-02-07abs ↗pdf ↗

In our model, nn traders interact with each other and with a central bank; they are taxed on the money they make, some of which is dissipated away by corruption. A generic feature of our model is that the richest trader always wins by 'consuming' all the others: another is the existence of a threshold wealth, below wh…

2005-04-18abs ↗pdf ↗

Public debates are a common platform for presenting and juxtaposing diverging views on important issues. In this work we propose a methodology for tracking how ideas flow between participants throughout a debate. We use this approach in a case study of Oxford-style debates---a competitive format where the winner is det…

2016-04-11abs ↗pdf ↗

We propose a simple change to existing neural network structures for better defending against gradient-based adversarial attacks. Instead of using popular activation functions (such as ReLU), we advocate the use of k-Winners-Take-All (k-WTA) activation, a C0 discontinuous function that purposely invalidates the neural …

2019-05-25abs ↗pdf ↗

AI predicts stock winners with 2.43 Sharpe ratio, but returns are highly concentrated.

problem Predicting stock returns with AI, focusing on identifying top winners.
method Deployed a state-of-the-art LLM to autonomously search the web for stock attractiveness, avoiding look-ahead bias.
result AI can generate alpha by identifying top winners, but returns are highly concentrated.

LoRA-MCL improves language models by generating diverse sentence continuations.

problem Language models struggle with generating diverse, plausible sentence continuations.
method Low-Rank Adaptation combined with Multiple Choice Learning (MCL) to handle ambiguity.
result LoRA-MCL generates high-diversity and relevant outputs in various tasks.

Inspired by the advances in biological science, the study of sparse binary projection models has attracted considerable recent research attention. The models project dense input samples into a higher-dimensional space and output sparse binary data representations after the Winner-Take-All competition, subject to the co…

2019-07-27abs ↗pdf ↗

A fast ML method solves complex combinatorial auction problems.

problem Solving winner determination in multi-unit combinatorial auctions.
method Graph Neural Network (GNN) with half-convolution operations for bid-item graph modeling.
result Approaches optimal performance with negligible revenue loss and low complexity.

Linear memory stores associations up to a logarithmic scale, but listwise retrieval can handle a quadratic scale.

problem How many key-value associations can a linear memory store?
method Analyzed linear memory models for top-1 and listwise retrieval, proving phase transitions and developing asymptotic theories.
result Linear memory has a logarithmic capacity for top-1 retrieval and a quadratic capacity for listwise retrieval.