Breakthroughs, discoveries, and DIY tips sent every weekday. Mitsubishi's bragging rights for designing the world's fastest Rubik's cube-solving robot have officially been stolen by a team of undergrads in Indiana. Earlier this month, Purdue University announced four collaborators in its Elmore Family School of Electrical and Computer Engineering (ECE) successfully designed and built a bot that not only set the new Guinness World Record--it absolutely demolished the multinational company's previous time. Meet Purdubik's Cube: a machine capable of completing a randomly shuffled Rubik's cube in just 0.103 seconds. At 1-2 times faster than the blink of a human eye, the feat is difficult to see, much less comprehend.

Financial transactions are increasingly being handled by automated programs called smart contracts. However, one challenge in the adaptation of smart contracts is the presence of vulnerabilities, which can cause significant monetary loss.

We study off-policy evaluation (OPE) in partially observable environments with complex observations, with the goal of developing estimators whose guarantee avoids exponential dependence on the horizon. While such estimators exist for MDPs and POMDPs can be converted to history-based MDPs, their estimation errors depend on the state-density ratio for MDPs which becomes history ratios after conversion, an exponential object. Recently, Uehara et al. [2022a] proposed future-dependent value functions as a promising framework to address this issue, where the guarantee for memoryless policies depends on the density ratio over the latent state space. However, it also depends on the boundedness of the futuredependent value function and other related quantities, which we show could be exponential-in-length and thus erasing the advantage of the method. In this paper, we discover novel coverage assumptions tailored to the structure of POMDPs, such as outcome coverage and belief coverage, which enable polynomial bounds on the aforementioned quantities. As a side product, our analyses also lead to the discovery of new algorithms with complementary properties.

We study the convergence behavior of a generalized Frank-Wolfe algorithm in constrained (stochastic) monotone variational inequality (MVI) problems. In recent years, there have been numerous efforts to design algorithms for solving constrained MVI problems due to their connections with optimization, machine learning, and equilibrium computation in games. Most work in this domain has focused on extensions of simultaneous gradient play, with particular emphasis on understanding the convergence properties of extragradient and optimistic gradient methods. In contrast, we examine the performance of an algorithm from another well-known class of optimization algorithms: Frank-Wolfe.

LLMs are increasingly fine-tuned using RLHF datasets to align them with human preferences and values. However, very limited research has investigated which specific human values are operationalized through these datasets. In this paper, we introduce Value Imprint, a framework for auditing and classifying the human values embedded within RLHF datasets. To investigate the viability of this framework, we conducted three case study experiments by auditing the Anthropic/hh-rlhf, OpenAI WebGPT Comparisons, and Alpaca GPT-4-LLM datasets to examine the human values embedded within them. Our analysis involved a two-phase process.

This paper explores the realm of infinite horizon average reward Constrained Markov Decision Processes (CMDPs). To the best of our knowledge, this work is the first to delve into the regret and constraint violation analysis of average reward CMDPs with a general policy parametrization. To address this challenge, we propose a primal dual-based policy gradient algorithm that adeptly manages the constraints while ensuring a low regret guarantee toward achieving a global optimal policy.

Large Language Model chatbots are increasingly taking the form and visage of human beings, adapting human faces, names, voices, personalities, and quirks, including those of celebrities and well-known political figures. Personifying AI chatbots could foreseeably increase their trust with users. However, it could also make them more capable of manipulation, by creating the illusion of a close and intimate relationship with an artificial entity. The European Commission has finalized the AI Act, with the EU Parliament making amendments banning manipulative and deceptive AI systems that cause significant harm to users. Although the AI Act covers harms that accumulate over time, it is unlikely to prevent harms associated with prolonged discussions with AI chatbots. Specifically, a chatbot could reinforce a person's negative emotional state over weeks, months, or years through negative feedback loops, prolonged conversations, or harmful recommendations, contributing to a user's deteriorating mental health.

Uncertainty is introduced in optimized DNNs through stochastic algorithms, forming specific distributions. Training models can be seen as random sampling from this distribution of optimized models. In this work, we study the distribution of optimized DNNs as a family of functions by leveraging a pointwise approach. We focus on the input saliency maps, as the input gradient field is decisive to the models' mathematical essence. Our investigation of saliency maps reveals a counter-intuitive trend: two stochastically optimized models tend to resemble each other more as either of their capacities increases. Therefore, we hypothesize several properties of these distributions, suggesting that (1) Within the same model architecture (e.g., CNNs, ResNets), different family variants (e.g., varying capacities) tend to align in terms of their population mean directions of the input salience.

We consider a constrained Markov Decision Problem (CMDP) where the goal of an agent is to maximize the expected discounted sum of rewards over an infinite horizon while ensuring that the expected discounted sum of costs exceeds a certain threshold.