Breakthroughs, discoveries, and DIY tips sent every weekday. It's something out of a dream or TV show: a married couple takes their dog for a walk and finds a buried treasure worth $10 million. But it actually happened, back in 2013. The treasure is the Saddle Ridge Hoard, the largest ever stash of gold coins found in the United States. The couple, who go by John and Mary in the press, have been careful to obscure their identity and the exact place where they live to prevent would-be treasure hunters from showing up on their property.

Your faves clockwise from top left: Clair Obscur: Expedition 33, Split Fiction, Death Stranding 2 and ARC Raiders. Your faves clockwise from top left: Clair Obscur: Expedition 33, Split Fiction, Death Stranding 2 and ARC Raiders. Once again, we are approaching the cherished time of year between Christmas and New Year when we might actually have the time to play some video games. I hope Santa brought you something new to play, instead of taking one look at all the unplayed games in your Steam library and putting you straight on the naughty list. Over the past few weeks you have been sending in your favourite games of the year.

Just over half (51%) of published novelists in the UK say that artificial intelligence is likely to end up entirely replacing their work as fiction writers, a new report from the University of Cambridge has found. Close to two-thirds (59%) of novelists say they know their work has been used to train AI Large Language Models (LLMs) without permission or payment. Over a third (39%) of novelists say their income has already taken a hit from generative AI, for example due to loss of other work that facilitates novel writing. Most (85%) novelists expect their future income to be driven down by AI. In new research for Cambridge's Minderoo Centre for Technology and Democracy (MCTD), Dr Clementine Collett surveyed 258 published novelists earlier this year, as well as 74 industry insiders - from commissioning editors to literary agents - to gauge how AI is viewed and used in the world of British fiction.*

Tuning hyperparameters is a crucial but arduous part of the machine learning pipeline. Hyperparameter optimization is even more challenging in federated learning, where models are learned over a distributed network of heterogeneous devices; here, the need to keep data on device and perform local training makes it difficult to efficiently train and evaluate configurations. In this work, we investigate the problem of federated hyperparameter tuning. We first identify key challenges and show how standard approaches may be adapted to form baselines for the federated setting. Then, by making a novel connection to the neural architecture search technique of weight-sharing, we introduce a new method, FedEx, to accelerate federated hyperparameter tuning that is applicable to widely-used federated optimization methods such as FedAvg and recent variants. Theoretically, we show that a FedEx variant correctly tunes the on-device learning rate in the setting of online convex optimization across devices. Empirically, we show that FedEx can outperform natural baselines for federated hyperparameter tuning by several percentage points on the Shakespeare, FEMNIST, and CIFAR-10 benchmarks--obtaining higher accuracy using the same training budget.

Transformers-based models, such as BERT, have been one of the most successful deep learning models for NLP. Unfortunately, one of their core limitations is the quadratic dependency (mainly in terms of memory) on the sequence length due to their full attention mechanism. To remedy this, we propose, BigBird, a sparse attention mechanism that reduces this quadratic dependency to linear. We show that BigBird is a universal approximator of sequence functions and is Turing complete, thereby preserving these properties of the quadratic, full attention model. Along the way, our theoretical analysis reveals some of the benefits of having $O(1)$ global tokens (such as CLS), that attend to the entire sequence as part of the sparse attention mechanism. The proposed sparse attention can handle sequences of length up to 8x of what was previously possible using similar hardware. As a consequence of the capability to handle longer context, BigBird drastically improves performance on various NLP tasks such as question answering and summarization. We also propose novel applications to genomics data.

The combination of deep reinforcement learning and search at both training and test time is a powerful paradigm that has led to a number of successes in single-agent settings and perfect-information games, best exemplified by AlphaZero. However, prior algorithms of this form cannot cope with imperfect-information games. This paper presents ReBeL, a general framework for self-play reinforcement learning and search that provably converges to a Nash equilibrium in any two-player zero-sum game. In the simpler setting of perfect-information games, ReBeL reduces to an algorithm similar to AlphaZero. Results in two different imperfect-information games show ReBeL converges to an approximate Nash equilibrium. We also show ReBeL achieves superhuman performance in heads-up no-limit Texas hold'em poker, while using far less domain knowledge than any prior poker AI.

We study a Markov matching market involving a planner and a set of strategic agents on the two sides of the market.At each step, the agents are presented with a dynamical context, where the contexts determine the utilities. The planner controls the transition of the contexts to maximize the cumulative social welfare, while the agents aim to find a myopic stable matching at each step.

We introduce the French Land cover from Aerospace ImageRy (FLAIR), an extensive dataset from the French National Institute of Geographical and Forest Information (IGN) that provides a unique and rich resource for large-scale geospatial analysis. FLAIR contains high-resolution aerial imagery with a ground sample distance of 20 cm and over 20 billion individually labeled pixels for precise land-cover classification.

How to Choose a Computer Monitor You Won't Hate in a Few Years PC monitors are cheaper, faster, and more beautiful than ever. Here's how to pick one that will suit your needs and budget. Most people treat their monitor like a printer. They just want it to work without having to think about it. But if you work from home or spend hours gaming every night, it's worth an upgrade. And that's where things can get complicated. Do you pay extra for more ports?

Continual learning agents experience a stream of (related) tasks. The main challenge is that the agent must not forget previous tasks and also adapt to novel tasks in the stream. We are interested in the intersection of two recent continual-learning scenarios. In meta-continual learning, the model is pre-trained using meta-learning to minimize catastrophic forgetting of previous tasks. In continual-meta learning, the aim is to train agents for faster remembering of previous tasks through adaptation.