MLINFO COLLECTION
Is there a fundamental tradeoff between desiderata for safe AI systems, such as harmlessness and helpfulness? We answer by formalizing the interaction between AI systems and users as a game with…
Allocating renewable resources fairly requires accounting for how present decisions affect future availability. We introduce Sustainable and Envy-Free Multi-Period Allocation, in which agents are…
In reservoir computing, performance depends on whether the fixed dynamics of the reservoir suit the task, and the appropriate memory length and frequency response differ across tasks. The reservoir…
For every fixed $\varepsilon\in(0,1)$ and $η\in[0,1)$, we prove that computing an $(\varepsilon,η)$-weak approximate Nash equilibrium requires quasipolynomial time assuming deterministic PPAD-ETH,…
We give the first unconditional family of polynomial-time algorithms that breaks the $1/3$ approximation barrier for symmetric bimatrix games. For every fixed $δ>0$, an algorithm in this family…
We establish dimension-free comparison inequalities between the Kullback-Leibler (KL) and $χ^2$-divergences and the squared Hellinger distance for Gaussian location mixtures with compactly supported…
We study simple auctions for one additive buyer whose values for $m$ items are independent. Write $\mathrm{REV}$ for optimal revenue, $\mathrm{SREV}$ and $\mathrm{BREV}$ for the revenues from…
Direct Preference Optimization (DPO) is widely used for offline Reinforcement Learning from Human Feedback. However, recent works have shown that DPO can be easily manipulated by adversarial…
General-sum games are more challenging than fully cooperative or adversarial settings because agents may deceive or exploit one another. Achieving high social welfare requires sustained cooperation,…
Blockchain participation games combine costly entry, random participation selection, and threshold success into consideration. Their retraction variants charge task-completion costs only to selected…
Automated market makers (AMMs) are central to decentralized exchanges, but their reserve curves make mechanism design different from classical double auctions. We study a batch double auction with…
In the classical principal-agent setting, the principal delegates some task to the agent, who receives a payment conditioned on the outcome of the task, which in turn benefits the principal. To align…
Duverger's law states that plurality elections tend to concentrate support on two candidates. Pivotal-voter models typically derive this from aggregate uncertainty about votes, so that two-candidate…
Motivated by applications in reinforcement learning from human feedback, we consider a setting where a given collection of rankings needs to be compressed into a smaller collection of rankings. This…
Vowpal Wabbitは、機械学習を進歩させるためのオンライン学習、ハッシュ、reduceなどの強力なアルゴリズムを含むシステムです。その結果、さまざまな問題に応じて、高品質な解決策を提供できます。
When robots are deployed in the real-world, they must interact with other agents and accomplish their own goals while adhering to legal constraints. These potentially conflicting objectives are often…
Existing feature attribution methods that account for feature dependencies do not scale to high dimensions. We propose causal integrated gradients (CIG) and causal expected gradients (CEG), which…
Query-conditioned probabilistic predictors answer logically related questions one at a time, and labels to check their calibration are often missing. For each restriction on what a bettor's stakes…
The Value Problem for weighted timed games, an extension of timed automata with weights and adversity, consists in determining, given a weighted timed game with a reachability objective and a…
P
We consider two linked problems for ranked choice elections: building a compact summary of a preference profile $P$, and generating synthetic profiles that resemble $P$ in key ways. We introduce a…
Accord is an arbitration oracle on Solana. Any Solana program can create an application specific court (i.e.
We study the route-set allocation problem between end nodes in capacity-constrained flow networks with transfer costs. We introduce an origin--destination (OD) bidding language, in which a…
Poset games form a fundamental class of combinatorial games that includes classical games such as Nim and Chomp. Determining the outcome of a poset game is known to be PSPACE-complete even for posets…