Online (bipartite) matching under known stationary arrivals is a fundamental model that has been studied extensively with the objective of maximizing the total number of customers served. We instead study the objective of maximizing the minimum matching rate across all online types, which is referred to as long-run (individual) fairness. For Online Matching under long-run Fairness (OM-LF) with a single offline agent, we show that the first-come-first-serve (FCFS) policy is 1-competitive, i.e., matching any optimal clairvoyant. For the general case of OM-LF: We present a sampling algorithm (SAMP) and show that (1) SAMP is of competitiveness of at least 1 1/e and (2) it is asymptotically optimal with competitiveness approaching one in different regimes when either all offline agents have a sufficiently large matching capacity, or all online types have a sufficiently large arrival rate, or highly imbalance between the total offline matching capacity and the number of online arrivals. To complement the competitive results, we show the following hardness results for OM-LF: (1) Any non-rejecting policy (matching every arriving online agent if possible) is no more than 1/2-competitive; (2) Any (randomized) policy is no more than ( 3 1)-competitive; (3) SAMP can be no more than (1 1/e)- competitive suggesting the tightness of competitive analysis for SAMP. We stress that all hardness results mentioned here are independent of any benchmarks. We also consider a few extensions of OM-LF by proposing a few variants of fairness metrics, including long-run group-level fairness and short-run fairness, and we devise related algorithms with provable competitive performance.

Welcome to Fox News' Artificial Intelligence newsletter with the latest AI technology advancements. IN TODAY'S NEWSLETTER: - Scammers can exploit your data from just one ChatGPT search - Business Insider embraces AI while laying off 21% of workforce - Nvidia, Dell partner with Trump admin to make next-gen supercomputer GUARD YOUR DATA: ChatGPT and other large language models (LLMs) have become amazing helpers for everyday tasks. Whether it's summarizing complex ideas, designing a birthday card or even planning your apartment's layout, you can get impressive results with just a simple prompt. NEWS BREAK: Business Insider announced Thursday that the company will be shrinking the size of its newsroom and making layoffs, impacting over a fifth of its staff. Business Insider CEO Barbara Peng said in an internal memo obtained by Fox News Digital that the company is "fully embracing AI," as 70% of the company's staff currently uses Enterprise ChatGPT, with a goal of 100%.

We consider online convex optimization with time-varying stage costs and additional switching costs. Since the switching costs introduce coupling across all stages, multi-step-ahead (long-term) predictions are incorporated to improve the online performance. However, longer-term predictions tend to suffer from lower quality. Thus, a critical question is: how to reduce the impact of long-term prediction errors on the online performance? To address this question, we introduce a gradient-based online algorithm, Receding Horizon Inexact Gradient (RHIG), and analyze its performance by dynamic regrets in terms of the temporal variation of the environment and the prediction errors. RHIG only considers at most W -stepahead predictions to avoid being misled by worse predictions in the longer term. The optimal choice of W suggested by our regret bounds depends on the tradeoff between the variation of the environment and the prediction accuracy. Additionally, we apply RHIG to a well-established stochastic prediction error model and provide expected regret and concentration bounds under correlated prediction errors. Lastly, we numerically test the performance of RHIG on quadrotor tracking problems.

We consider online convex optimization with time-varying stage costs and additional switching costs. Since the switching costs introduce coupling across all stages, multi-step-ahead (long-term) predictions are incorporated to improve the online performance. However, longer-term predictions tend to suffer from lower quality. Thus, a critical question is: how to reduce the impact of long-term prediction errors on the online performance? To address this question, we introduce a gradient-based online algorithm, Receding Horizon Inexact Gradient (RHIG), and analyze its performance by dynamic regrets in terms of the temporal variation of the environment and the prediction errors. RHIG only considers at most W -stepahead predictions to avoid being misled by worse predictions in the longer term. The optimal choice of W suggested by our regret bounds depends on the tradeoff between the variation of the environment and the prediction accuracy. Additionally, we apply RHIG to a well-established stochastic prediction error model and provide expected regret and concentration bounds under correlated prediction errors. Lastly, we numerically test the performance of RHIG on quadrotor tracking problems.

In this section, we provide the details of the image operations that were used in our search space for augmentation policies, a sensibility test for the EMA decay parameter α in our model, and our procedure of reducing the search space of augmentation policies is explained. Finally, we provide some additional experiments for evaluation of our proposed method.

Fox News chief Washington correspondent Mike Emanuel has the latest on Transportation Secretary Sean Duffy's statements about recent air traffic control incidents on'Special Report.' Transportation Secretary Sean Duffy recently announced that artificial intelligence (AI) is being used to detect and address air traffic risks, following a slew of near-misses and fatal plane crashes across the country. Duffy told FOX 5 DC that officials are implementing AI to "identify and address potential air traffic risks nationwide," potentially aiding in preventing tragedies like the fatal Jan. 29 midair collision at Ronald Reagan Washington National Airport (DCA) that claimed the lives of 67 people. Following the Potomac River crash, which involved a commercial plane and an Army Black Hawk helicopter, Duffy announced a plan to build a new "state-of-the-art" traffic control system that will equip locations with better technology to reduce outages, improve efficiency and reinforce safety. Duffy told FOX 5 that when investigators were looking into how to prevent collisions, they asked themselves, "Are there any other DCAs out there?" Transportation Secretary Sean Duffy speaks during a news conference following up on the issuance of the National Transportation Safety Board preliminary report on the mid-air collision near Ronald Reagan Washington National Airport, on Tuesday, March 11.

Frontier AI systems, including large language models (LLMs), hold increasing influence over the epistemology of human users. Such influence can reinforce prevailing societal values, potentially contributing to the lock-in of misguided moral beliefs and, consequently, the perpetuation of problematic moral practices on a broad scale. We introduce progress alignment as a technical solution to mitigate this imminent risk. Progress alignment algorithms learn to emulate the mechanics of human moral progress, thereby addressing the susceptibility of existing alignment methods to contemporary moral blindspots.

We consider the problem of hypothesis testing for discrete distributions. In the standard model, where we have sample access to an underlying distribution p, extensive research has established optimal bounds for uniformity testing, identity testing (goodness of fit), and closeness testing (equivalence or two-sample testing). We explore these problems in a setting where a predicted data distribution, possibly derived from historical data or predictive machine learning models, is available. We demonstrate that such a predictor can indeed reduce the number of samples required for all three property testing tasks. The reduction in sample complexity depends directly on the predictor's quality, measured by its total variation distance from p.

Humans and animals have the ability to reason and make predictions about different courses of action at many time scales. In reinforcement learning, option models (Sutton, Precup & Singh, 1999; Precup, 2000) provide the framework for this kind of temporally abstract prediction and reasoning. Natural intelligent agents are also able to focus their attention on courses of action that are relevant or feasible in a given situation, sometimes termed affordable actions. In this paper, we define a notion of affordances for options, and develop temporally abstract partial option models, that take into account the fact that an option might be affordable only in certain situations. We analyze the trade-offs between estimation and approximation error in planning and learning when using such models, and identify some interesting special cases. Additionally, we empirically demonstrate the ability to learn both affordances and partial option models online resulting in improved sample efficiency and planning time in the Taxi domain.