Author name cluster

Milan Mossé

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

4 papers

2 author rows

AAAI Conference 2026 Conference Paper

Stable Voting and the Splitting of Cycles

Wesley H. Holliday
Milan Mossé
Chase Norman
Eric Pacuit
Cynthia Wang

Algorithms for resolving majority cycles in preference aggregation have been studied extensively in computational social choice. Several sophisticated cycle-resolving methods, including Tideman's Ranked Pairs, Schulze's Beat Path, and Heitzig's River, are refinements of the Split Cycle (SC) method that resolves majority cycles by discarding the weakest majority victories in each cycle. Recently, Holliday and Pacuit proposed a new refinement of Split Cycle, dubbed Stable Voting, and a simplification thereof, called Simple Stable Voting (SSV). They conjectured that SSV is a refinement of SC whenever no two majority victories are of the same size. In this paper, we prove the conjecture up to 6 alternatives and refute it for more than 6 alternatives. While our proof of the conjecture for up to 5 alternatives uses traditional mathematical reasoning, our 6-alternative proof and 7-alternative counterexample were obtained with the use of SAT solving. The SAT encoding underlying this proof and counterexample is applicable far beyond SC and SSV: it can be used to test properties of any voting method whose choice of winners depends only on the ordering of margins of victory by size.

PDF Details DOI

ICML Conference 2024 Conference Paper

Position: Social Choice Should Guide AI Alignment in Dealing with Diverse Human Feedback

Vincent Conitzer
Rachel Freedman
Jobst Heitzig
Wesley H. Holliday
Bob M. Jacobs
Nathan O. Lambert
Milan Mossé
Eric Pacuit

Foundation models such as GPT-4 are fine-tuned to avoid unsafe or otherwise problematic behavior, such as helping to commit crimes or producing racist text. One approach to fine-tuning, called reinforcement learning from human feedback, learns from humans’ expressed preferences over multiple outputs. Another approach is constitutional AI, in which the input from humans is a list of high-level principles. But how do we deal with potentially diverging input from humans? How can we aggregate the input into consistent data about “collective” preferences or otherwise use it to make collective choices about model behavior? In this paper, we argue that the field of social choice is well positioned to address these questions, and we discuss ways forward for this agenda, drawing on discussions in a recent workshop on Social Choice for AI Ethics and Safety held in Berkeley, CA, USA in December 2023.

Details

SAT Conference 2022 Conference Paper

A Generalization of the Satisfiability Coding Lemma and Its Applications

Milan Mossé
Harry Sha
Li-Yang Tan

The seminal Satisfiability Coding Lemma of Paturi, Pudlák, and Zane is a coding scheme for satisfying assignments of k-CNF formulas. We generalize it to give a coding scheme for implicants and use this generalized scheme to establish new structural and algorithmic properties of prime implicants of k-CNF formulas. Our first application is a near-optimal bound of n⋅ 3^{n(1-Ω(1/k))} on the number of prime implicants of any n-variable k-CNF formula. This resolves an open problem from the Ph. D. thesis of Talebanfard, who proved such a bound for the special case of constant-read k-CNF formulas. Our proof is algorithmic in nature, yielding an algorithm for computing the set of all prime implicants - the Blake Canonical Form - of a given k-CNF formula. The problem of computing the Blake Canonical Form of a given function is a classic one, dating back to Quine, and our work gives the first non-trivial algorithm for k-CNF formulas.

Details

ICLR Conference 2021 Conference Paper

Conditional Negative Sampling for Contrastive Learning of Visual Representations

Mike Wu
Milan Mossé
Chengxu Zhuang
Daniel L. K. Yamins
Noah D. Goodman

Recent methods for learning unsupervised visual representations, dubbed contrastive learning, optimize the noise-contrastive estimation (NCE) bound on mutual information between two transformations of an image. NCE typically uses randomly sampled negative examples to normalize the objective, but this may often include many uninformative examples either because they are too easy or too hard to discriminate. Taking inspiration from metric learning, we show that choosing semi-hard negatives can yield stronger contrastive representations. To do this, we introduce a family of mutual information estimators that sample negatives conditionally -- in a "ring" around each positive. We prove that these estimators remain lower-bounds of mutual information, with higher bias but lower variance than NCE. Experimentally, we find our approach, applied on top of existing models (IR, CMC, and MoCo) improves accuracy by 2-5% absolute points in each case, measured by linear evaluation on four standard image benchmarks. Moreover, we find continued benefits when transferring features to a variety of new image distributions from the Meta-Dataset collection and to a variety of downstream tasks such as object detection, instance segmentation, and key-point detection.

Details