Welcome to our monthly digest, where you can catch up with any AIhub stories you may have missed, peruse the latest news, recap recent events, and more. This month, we learn about AI for science, delve into world models, research transparent and trustworthy AI, and hear about the lottery ticket hypothesis. The latest interview in our series with the AAAI/SIGAI Doctoral Consortium participants featured Ximing Wen who is researching transparent and trustworthy AI systems. We found out more about her work, her experience as a research intern, and what inspired her to study AI. In this wide-ranging conversation, Jonathan Frankle delves into empiricism versus theoretical proofs, how the approach to computer science has changed (even if the fundamental problems haven't), how younger researchers are rapidly adapting to a world that values impact above all else, and what it means to be a researcher.

Quantum machine learning (QML) aims to accelerate machine learning tasks by exploiting quantum computation. Previous work studied a QML algorithm for selecting sparse subnetworks from large shallow neural networks. Instead of directly solving an optimization problem over a large-scale network, this algorithm constructs a sparse subnetwork by sampling hidden nodes from an optimized probability distribution defined using the ridgelet transform. The quantum algorithm performs this sampling in time $O(D)$ in the data dimension $D$, whereas a naive classical implementation relies on handling exponentially many candidate nodes and hence takes $\exp[O(D)]$ time. In this work, we construct and analyze a quantum-inspired fully classical algorithm for the same sampling task. We show that our algorithm runs in time $O(\operatorname{poly}(D))$, thereby removing the exponential dependence on $D$ from the previous classical approach. Numerical simulations show that the proposed sampler achieves empirical risk comparable to exact sampling from the optimized distribution and substantially lower than sampling from the non-optimized uniform distribution, while also exhibiting exponentially improved runtime scaling compared with the conventional classical implementation. These successful dequantization results show that sparse subnetwork selection via optimized sampling can be achieved classically with polynomial data-dimension scaling on conventional computers without quantum hardware, providing an alternative to the existing quantum algorithm.

Neural Information Processing Systems http://nips.cc/

Work was done when the author interned at Microsoft.

Recent memoirs by the retired bookie Art Manteris and the storied gambler Billy Walters provide a glimpse of an industry in its fledgling form--and a preview of the DraftKings era to come. Las Vegas is no longer the seat of the sportsbook gods. In most states, it's now legal, and extremely popular, to place bets using apps or websites such as FanDuel and DraftKings. From your couch, you can wager on everything from the results of snooker championships to the color of the Gatorade poured over the victorious coach after the Super Bowl. The N.F.L., along with the other major-league American sports associations, has officially partnered with sports-betting sites, and their alliance has proved so lucrative that other industries want in on the action; last month, the Golden Globes made a deal with Polymarket, a predictions-market platform, to encourage wagering (or "trading," if you prefer) on the outcomes of its awards race.

Is AI taking the fun out of fantasy football? For years, fantasy football has given every armchair manager the space to back up claims they could do a better job than the real thing. Whether you're competing against workmates, family members or strangers, the ability to pull together your own dream team is irresistible to millions of football fans. The competitive pastime has spawned a whole industry of content creators offering weekly tips for anyone looking to gain an edge as they sift through stats and manage transfers. Recently, more players have been turning to Artificial Intelligence (AI) tools for advice - but not everyone agrees they have a place in the virtual dugout.

As there exist competitive subnetworks within a dense network in concert with Lottery Ticket Hypothesis, we introduce a novel neuron-wise task incremental learning method, namely Data-free Subnetworks (DSN), which attempts to enhance the elastic knowledge transfer across the tasks that sequentially arrive. Specifically, DSN primarily seeks to transfer knowledge to the new coming task from the learned tasks by selecting the affiliated weights of a small set of neurons to be activated, including the reused neurons from prior tasks via neuron-wise masks. And it also transfers possibly valuable knowledge to the earlier tasks via data-free replay.

The recently developed sparse network training methods, such as Lottery Ticket Hypothesis (LTH) and its variants, have shown impressive learning capacity by finding sparse sub-networks from a dense one. While these methods could largely sparsify deep networks, they generally focus more on realizing comparable accuracy to dense counterparts yet neglect network calibration. However, how to achieve calibrated network predictions lies at the core of improving model reliability, especially when it comes to addressing the overconfident issue and out-of-distribution cases. In this study, we propose a novel Distributionally Robust Optimization (DRO) framework to achieve an ensemble of lottery tickets towards calibrated network sparsification. Specifically, the proposed DRO ensemble aims to learn multiple diverse and complementary sparse sub-networks (tickets) with the guidance of uncertainty sets, which encourage tickets to gradually capture different data distributions from easy to hard and naturally complement each other. We theoretically justify the strong calibration performance by showing how the proposed robust training process guarantees to lower the confidence of incorrect predictions. Extensive experimental results on several benchmarks show that our proposed lottery ticket ensemble leads to a clear calibration improvement without sacrificing accuracy and burdening inference costs. Furthermore, experiments on OOD datasets demonstrate the robustness of our approach in the open-set environment.