We introduce GAUCHE, an open-source library for GAUssian processes in CHEmistry. Gaussian processes have long been a cornerstone of probabilistic machine learning, affording particular advantages for uncertainty quantification and Bayesian optimisation. Extending Gaussian processes to molecular representations, however, necessitates kernels defined over structured inputs such as graphs, strings and bit vectors. By providing such kernels in a modular, robust and easy-to-use framework, we seek to enable expert chemists and materials scientists to make use of state-of-the-art black-box optimization techniques. Motivated by scenarios frequently encountered in practice, we showcase applications for GAUCHE in molecular discovery, chemical reaction optimisation and protein design.

Unsupervised reinforcement learning aims at learning a generalist policy in a reward-free manner for fast adaptation to downstream tasks. Most of the existing methods propose to provide an intrinsic reward based on surprise. Maximizing or minimizing surprise drives the agent to either explore or gain control over its environment. However, both strategies rely on a strong assumption: the entropy of the environment's dynamics is either high or low. This assumption may not always hold in real-world scenarios, where the entropy of the environment's dynamics may be unknown. Hence, choosing between the two objectives is a dilemma. We propose a novel yet simple mixture of policies to address this concern, allowing us to optimize an objective that simultaneously maximizes and minimizes the surprise. Concretely, we train one mixture component whose objective is to maximize the surprise and another whose objective is to minimize the surprise. Hence, our method does not make assumptions about the entropy of the environment's dynamics.

Training large language models with FP8 formats offers significant efficiency gains. However, the reduced numerical precision of FP8 poses challenges for stable and accurate training. Current frameworks preserve training performance using mixed-granularity quantization, i.e., applying per-group quantization for activations and per-tensor/block quantization for weights. While effective, per-group quantization requires scaling along the inner dimension of matrix multiplication, introducing additional dequantization overhead. Moreover, these frameworks often rely on just-in-time scaling to dynamically adjust scaling factors based on the current data distribution. However, this online quantization is inefficient for FP8 training, as it involves multiple memory reads and writes that negate the performance benefits of FP8. To overcome these limitations, we propose MOSS, a novel FP8 training framework that ensures both efficiency and numerical stability. MOSS introduces two key innovations: (1) a two-level microscaling strategy for quantizing sensitive activations, which balances precision and dequantization cost by combining a high-precision global scale with compact, power-of-two local scales; and (2) automatic scaling for weights in linear layers, which eliminates the need for costly max-reduction operations by predicting and adjusting scaling factors during training. Leveraging these techniques, MOSS enables efficient FP8 training of a 7B parameter model, achieving performance comparable to the BF16 baseline while achieving up to 34% higher training throughput. Large language models (LLMs) have demonstrated remarkable capabilities across diverse tasks, including reasoning, language understanding, and generation (Achiam et al., 2023; Grattafiori et al., 2024; Liu et al., 2024; Adler et al., 2024).

Statistical inference from data generated by multi-armed bandit (MAB) algorithms is challenging due to their adaptive, non-i.i.d. nature. A classical manifestation is that sample averages of arm rewards under bandit sampling may fail to satisfy a central limit theorem. Lai and Wei's stability condition provides a sufficient, and essentially necessary criterion, for asymptotic normality in bandit problems. While the celebrated Upper Confidence Bound (UCB) algorithm satisfies this stability condition, it is not minimax optimal, raising the question of whether minimax optimality and statistical stability can be achieved simultaneously. In this paper, we analyze the stability properties of a broad class of bandit algorithms that are based on the optimism principle. We establish general structural conditions under which such algorithms violate the Lai-Wei stability criterion. As a consequence, we show that widely used minimax-optimal UCB-style algorithms, including MOSS, Anytime-MOSS, Vanilla-MOSS, ADA-UCB, OC-UCB, KL-MOSS, KL-UCB++, KL-UCB-SWITCH, and Anytime KL-UCB-SWITCH, are unstable. We further complement our theoretical results with numerical simulations demonstrating that, in all these cases, the sample means fail to exhibit asymptotic normality. Overall, our findings suggest a fundamental tension between stability and minimax optimal regret, raising the question of whether it is possible to design bandit algorithms that achieve both. Understanding whether such simultaneously stable and minimax optimal strategies exist remains an important open direction.

After defying multiple mass extinctions on Earth, the hardy plant passes an intergalactic test. Breakthroughs, discoveries, and DIY tips sent every weekday. While it may appear humble, Earth's moss is built darn tough. It thrives in extreme environments -from the bitter cold, low-oxygen air of the Himalayas, down to the parched sands of Death Valley. Some species even make their home among the lava fields of active volcanoes .

These hyperparameters are fixed throughout all domains. Tab. 1 details the hyper-parameters used in MOSS which are taken directly from We include the environment renders in Figure?? . 1 Table 2: Hyperparameters for MOSS and DQN. These hyperparameters are fixed throughout all domains. Action repeat 1 Frame repeat 12 Seed frames 4000 n-step returns 3 Mini-batch size 1048 Discount ( γ) 0.99 Optimizer Adam Learning rate 0.0001 Agent update frequency 2 Critic target EMA rate ( τ We made modifications to MOSS to evaluate in discrete action settings. Tab. 2 details the hyper-parameters used for Double DQN and MOSS in the ViZDoom environment.

Hence, choosing between the two objectives is a dilemma.

We study a regret minimization problem with the existence of multiple best/near-optimal arms in the multi-armed bandit setting.

Botanists say detectives are overlooking a potentially vital source of crime scene evidence. Breakthroughs, discoveries, and DIY tips sent every weekday. Moss is one of the world's oldest and most basic plants. Part of the bryophyte family, the estimated 12,000 known moss species have evolved over millions of years to flourish without seeds, leaves, stems, or even roots. This allows the sturdy plants to absorb all their water and nutrients from the environment around them.

Scientists were out to prove sleep was just a waste of time. Among the students who participated in the sleep deprivation study was the future head of the psychology department at George Washington University. Breakthroughs, discoveries, and DIY tips sent every weekday. The grueling Medical College Admission Test, or MCAT, was first devised in the 1920s by George Washington University professor Frederick August Moss. Originally called the Scholastic Aptitude Test for Medical Students, Moss developed the readiness test as a way to curb high dropout rates in medical schools.