We consider a contextual bandit problem with S contexts and K actions. In each round t = 1,2,... the learner observes a random context and chooses an action based on its past experience. The learner then observes a random reward whose mean is a function of the context and the action for the round. Under the assumption that the contexts can be lumped into r min{S,K}groups such that the mean reward for the various actions is the same for any two contexts that are in the same group, we give an algorithm that outputs an ε-optimal policy after using at most eO(r(S+K)/ε2) samples with high probability and provide a matching Ω(r(S + K)/ε2) lower bound. In the regret minimization setting, we give an algorithm whose cumulative regret up to time T is bounded by eO( p r3(S+K)T). To the best of our knowledge, we are the first to show the near-optimal sample complexity in the PAC setting and eO( p poly(r)(S+K)T)minimax regret in the online setting for this problem. We also show our algorithms can be applied to more general low-rank bandits and get improved regret bounds in some scenarios.

Scientists recently unveiled a new robot that can detect when an older person is losing their balance and catch them before they fall - a potential breakthrough in a world where the portion of people over 60 years old will nearly double to 22% by 2050. The device, which researchers hope to begin selling within the next year, resembles a motorized scooter and is equipped with in-built sensors as well as a harness that patients can wear around their hips. It's been dubbed Mr. Bah, which is shorthand for mobile robot balance assistant. The device could have a broad impact, since the CDC reports that falls are the leading cause of injury-related deaths among people over 65. A man demonstrates the capabilities of Mr. Bah, a robot that can catch an elderly person before they fall Developed by researchers at Nanyang Technological University and Tan Tock Seng Hospital (TTSH) in Singapore, the robot would also help those who have a hard time walking and balancing to stand up safely from a seated position.

AI has finally settled into the mainstream. Successful proof-of-concepts have emerged in a number of industries, and there have been many examples of successful plant-floor deployments of AI. Some organizations have applied AI/ML projects across the enterprise to complete pipelines. This overall maturity is changing the way companies view the strategic value of AI and the areas in which they want its benefits to be realized. Let's look at 10 AI company strategy trends currently diagnosed by industry experts.

A teenager in New York is suing one of the biggest companies in the world for $1 billion. A New York college student filed a lawsuit against Apple for $1 billion, claiming the company's alleged use of facial recognition software in its stores falsely linked him to a series of Apple store thefts. Ousmane Bah, 18, claims that he received a summons from a court in Boston saying that he stole $1,200 worth of Apple products in 2018, according to papers filed on Monday in Manhattan federal court. The products included Apple Pencils, which retail for $99 each. On the day of one of the thefts in Boston, Bah was attending his senior prom in Manhattan, according to the court documents.

Ousmane Bah, an 18-year-old college student from New York, filed a lawsuit against Apple on Monday for allegedly relying on facial recognition systems that misidentified him as a serial shoplifter. The suit claims that Apple and its contractor, Security Industry Specialists, caused Bah to suffer emotional distress as a result. Apple has subsequently denied that it uses facial recognition in its stores. According to the lawsuit, Bah received a summons arraignment last summer from a Boston municipal court for the theft of $1,200 worth of products from an Apple Store in the city. The police report indicated that a Security Industry Specialists loss prevention associate saw the theft on a security video and recognized Bah from a similar incident at an Apple Store in Connecticut.