Search

A central goal of cryptography is Secure Multi-party Computation (MPC), where $n$ parties desire to compute a function of their joint inputs without letting any party learn about the inputs of its peers. Unfortunately, it is well-known that MPC guaranteeing output delivery to every party is infeasible when a majority of the parties are malicious. In fact, parties operating over a point-to-point network (i.e. without access to a broadcast channel) cannot even reach an agreement on the output when more than one third of the parties are malicious (Lamport, Shostak, and Pease, JACM 1980). Motivated by this infeasibility in the point-to-point model, Goldwasser and Lindell (J. Cryptol 2005) introduced a definition of MPC that does not require agreement, referred to as MPC with selective abort. Under this definition, any party may abort the protocol if they detect malicious behavior. They showed that MPC with selective abort is feasible for any number of malicious parties by implementing a broadcast functionality with abort. While the model of MPC with abort has attracted much attention over the years, little is known about its communication complexity over point-to-point networks. In this work, we study the communication complexity of MPC with abort and devise nearly-optimal communication efficient protocols in this model. Namely, we prove trade-offs between the number of honest parties $h$, the communication complexity, and the locality of the protocols. Here, locality is a bound on the number of peers with which each party must communicate., Comment: 13 pages, abstract shortened. PODC 2024

How can we trust the correctness of a learned model on a particular input of interest? Model accuracy is typically measured *on average* over a distribution of inputs, giving no guarantee for any fixed input. This paper proposes a theoretically-founded solution to this problem: to train *Self-Proving models* that prove the correctness of their output to a verification algorithm $V$ via an Interactive Proof. Self-Proving models satisfy that, with high probability over a random input, the model generates a correct output *and* successfully proves its correctness to $V\!$. The *soundness* property of $V$ guarantees that, for *every* input, no model can convince $V$ of the correctness of an incorrect output. Thus, a Self-Proving model proves correctness of most of its outputs, while *all* incorrect outputs (of any model) are detected by $V$. We devise a generic method for learning Self-Proving models, and we prove convergence bounds under certain assumptions. The theoretical framework and results are complemented by experiments on an arithmetic capability: computing the greatest common divisor (GCD) of two integers. Our learning method is used to train a Self-Proving transformer that computes the GCD *and* proves the correctness of its answer.

This is a report on JamCoders, a four-week long computer-science camp for high school students in Jamaica. The camp teaches college-level coding and algorithms, and targets academically excellent students in grades 9--11 (ages 14--17). Qualitative assessment shows that the camp was, in general terms, a success. We reflect on the background and academic structure of the camp and share key takeaways on designing and operating a successful camp. We analyze data collected before, during and after the camp and map the effects of demographic differences on student performance in camp. We conclude with a discussion on possible improvements on our approach., Comment: To appear in Proceedings of the 55th ACM Technical Symposium on Computer Science Education (SIGCSE), 2024

With large language models surpassing human performance on an increasing number of benchmarks, we must take a principled approach for targeted evaluation of model capabilities. Inspired by pseudorandomness, we propose pseudointelligence, which captures the maxim that "(perceived) intelligence lies in the eye of the beholder". That is, that claims of intelligence are meaningful only when their evaluator is taken into account. Concretely, we propose a complexity-theoretic framework of model evaluation cast as a dynamic interaction between a model and a learned evaluator. We demonstrate that this framework can be used to reason about two case studies in language model evaluation, as well as analyze existing evaluation methods., Comment: EMNLP 2023 Findings

Neural networks are capable of translating between languages -- in some cases even between two languages where there is little or no access to parallel translations, in what is known as Unsupervised Machine Translation (UMT). Given this progress, it is intriguing to ask whether machine learning tools can ultimately enable understanding animal communication, particularly that of highly intelligent animals. We propose a theoretical framework for analyzing UMT when no parallel translations are available and when it cannot be assumed that the source and target corpora address related subject domains or posses similar linguistic structure. We exemplify this theory with two stylized models of language, for which our framework provides bounds on necessary sample complexity; the bounds are formally proven and experimentally verified on synthetic data. These bounds show that the error rates are inversely related to the language complexity and amount of common ground. This suggests that unsupervised translation of animal communication may be feasible if the communication system is sufficiently complex.

Randomly masking and predicting word tokens has been a successful approach in pre-training language models for a variety of downstream tasks. In this work, we observe that the same idea also applies naturally to sequential decision-making, where many well-studied tasks like behavior cloning, offline reinforcement learning, inverse dynamics, and waypoint conditioning correspond to different sequence maskings over a sequence of states, actions, and returns. We introduce the UniMASK framework, which provides a unified way to specify models which can be trained on many different sequential decision-making tasks. We show that a single UniMASK model is often capable of carrying out many tasks with performance similar to or better than single-task models. Additionally, after fine-tuning, our UniMASK models consistently outperform comparable single-task models. Our code is publicly available at https://github.com/micahcarroll/uniMASK., Comment: NeurIPS 2022 (Oral). A prior version was published at an ICML Workshop, available at arXiv:2204.13326

Randomly masking and predicting word tokens has been a successful approach in pre-training language models for a variety of downstream tasks. In this work, we observe that the same idea also applies naturally to sequential decision making, where many well-studied tasks like behavior cloning, offline RL, inverse dynamics, and waypoint conditioning correspond to different sequence maskings over a sequence of states, actions, and returns. We introduce the FlexiBiT framework, which provides a unified way to specify models which can be trained on many different sequential decision making tasks. We show that a single FlexiBiT model is simultaneously capable of carrying out many tasks with performance similar to or better than specialized models. Additionally, we show that performance can be further improved by fine-tuning our general model on specific tasks of interest., Comment: Superseded by arXiv:2211.10869