Recent work on deriving $O(\log T)$ anytime regret bounds for stochastic dueling bandit problems has considered mostly Condorcet winners, which do not always exist, and more recently, winners defined by the Copeland set, which do always exist. In this work, we consider a broad notion of winners defined by tournament solutions in social choice theory, which include the Copeland set as a special case but also include several other notions of winners such as the top cycle, uncovered set, and Banks set, and which, like the Copeland set, always exist. We develop a family of UCB-style dueling bandit algorithms for such general tournament solutions, and show $O(\log T)$ anytime regret bounds for them. Experiments confirm the ability of our algorithms to achieve low regret relative to the target winning set of interest.

Neural Information Processing Systems http://nips.cc/

Breakthroughs, discoveries, and DIY tips sent every weekday. The ticking tyranny of 2 a.m. after you climbed into bed–responsibly–at 11. As the minutes go by, all you can think about is the importance of good sleep for function, mood, and productivity. What's worse, the big white letters on your sleep score will read "poor" like a middle school quiz. And while health-tracking devices have helped many gain insight into their bodies, hyperfixation on sleep metrics can backfire.

Aggregating preferences under incomplete or constrained feedback is a fundamental problem in social choice and related domains. While prior work has established strong impossibility results for pairwise comparisons, this paper extends the inquiry to improvement feedback, where voters express incremental adjustments rather than complete preferences. We provide a complete characterization of the positional scoring rules that can be computed given improvement feedback. Interestingly, while plurality is learnable under improvement feedback--unlike with pairwise feedback--strong impossibility results persist for many other positional scoring rules. Furthermore, we show that improvement feedback, unlike pairwise feedback, does not suffice for the computation of any Condorcet-consistent rule. We complement our theoretical findings with experimental results, providing further insights into the practical implications of improvement feedback for preference aggregation.

Can neural networks be applied in voting theory, while satisfying the need for transparency in collective decisions? We propose axiomatic deep voting: a framework to build and evaluate neural networks that aggregate preferences, using the well-established axiomatic method of voting theory. Our findings are: (1) Neural networks, despite being highly accurate, often fail to align with the core axioms of voting rules, revealing a disconnect between mimicking outcomes and reasoning. (2) Training with axiom-specific data does not enhance alignment with those axioms. (3) By solely optimizing axiom satisfaction, neural networks can synthesize new voting rules that often surpass and substantially differ from existing ones. This offers insights for both fields: For AI, important concepts like bias and value-alignment are studied in a mathematically rigorous way; for voting theory, new areas of the space of voting rules are explored.

We consider the problem of recovering the ground truth ordering (ranking, top-$k$, or others) over a large number of alternatives. The wisdom of crowd is a heuristic approach based on Condorcet's Jury theorem to address this problem through collective opinions. This approach fails to recover the ground truth when the majority of the crowd is misinformed. The surprisingly popular (SP) algorithm cite{prelec2017solution} is an alternative approach that is able to recover the ground truth even when experts are in minority. The SP algorithm requires the voters to predict other voters' report in the form of a full probability distribution over all rankings of alternatives. However, when the number of alternatives, $m$, is large, eliciting the prediction report or even the vote over $m$ alternatives might be too costly. In this paper, we design a scalable alternative of the SP algorithm which only requires eliciting partial preferences from the voters, and propose new variants of the SP algorithm. In particular, we propose two versions -- Aggregated-SP and Partial-SP -- that ask voters to report vote and prediction on a subset of size $k$ ($\ll m$) in terms of top alternative, partial rank, or an approval set. Through a large-scale crowdsourcing experiment on MTurk, we show that both of our approaches outperform conventional preference aggregation algorithms for the recovery of ground truth rankings, when measured in terms of Kendall-Tau distance and Spearman's $\rho$. We further analyze the collected data and demonstrate that voters' behavior in the experiment, including the minority of the experts, and the SP phenomenon, can be correctly simulated by a concentric mixtures of Mallows model. Finally, we provide theoretical bounds on the sample complexity of SP algorithms with partial rankings to demonstrate the theoretical guarantees of the proposed methods.

Elon Musk captured the imaginations of the world this week when he revealed one of the first volunteers to have his brain chip implanted in their skulls. But the historic moment is only possible thanks to decades of pioneering scientists and brave subjects that came before it - who had brain-computer interface chips into people's brains, with much more primitive tech. Musk has said he hopes that in the very near future his Neuralink device will enable people to control a computer cursor or keyboard with their brain to communicate, like'replacing a piece of the skull with a smartwatch.' Musk has said he hopes that in the very near future his Neuralink device will enable people to control a computer cursor or keyboard with their brain to communicate, like'replacing a piece of the skull with a smartwatch.' Ultimately, brain-computer interface devices offer the promise of giving disabled people the ability to see, touch, speak, and perform tasks again - and some proponents like Musk see an ultimate goal of all of humanity merging with tech in future. His device builds on the foundation built by tech that was pioneered in 2006 and allowed a paralyzed man to move a computer mouse with his brain a whole decade before Neuralink was founded.

For decades, real estate commissions have been somewhat standardized, with most home sellers paying 5% to 6% commission to cover both the listing agent and the buyer's agent. A landmark agreement from the National Assn. of Realtors paved the way for a new set of rules that will likely shake up the entire industry, affecting sellers, buyers and the agents tasked with pushing deals across the finish line. The most pivotal rule change pertains to how buyers' agents are paid. Traditionally, home sellers have paid for the commission of both their agent and the buyer's agent, which critics argue stifled competition and drove up home prices. The new rule prohibits most listings from saying how much buyers' agents are paid, removing the assumption that sellers are on the hook for paying both agents.

Recent work on deriving O(log T) anytime regret bounds for stochastic dueling bandit problems has considered mostly Condorcet winners, which do not always exist, and more recently, winners defined by the Copeland set, which do always exist. In this work, we consider a broad notion of winners defined by tournament solutions in social choice theory, which include the Copeland set as a special case but also include several other notions of winners such as the top cycle, uncovered set, and Banks set, and which, like the Copeland set, always exist. We develop a family of UCB-style dueling bandit algorithms for such general tournament solutions, and show O(log T) anytime regret bounds for them. Experiments confirm the ability of our algorithms to achieve low regret relative to the target winning set of interest.