For additional motivation, it is reasonable to consider Massart noise to be a more realistic model of real-life noise (even when benign) when compared to the RCN model, as it allows for some amount of non-uniformity. This made Definition 1 a possibly tractable way to relax the noise assumption, without running intotheaforementioned computational barriers foragnostic learning.

Yet they are still far from true intelligence, which opens up intriguing opportunities to explore the parallels of humans and modelbehaviors.

The generation of equilibrium samples of molecular systems has been a longstanding problem in statistical physics.

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

Applied work with interference typically models outcomes as functions of own treatment and a low-dimensional exposure mapping of others' treatments, even when that mapping may be misspecified. This raises a basic question: what policy object are exposure-based estimands implicitly targeting, and how should we interpret their direct and spillover components relative to the underlying policy question? We take as primitive the marginal policy effect, defined as the effect of a small change in the treatment probability under the actual experimental design, and show that any researcher-chosen exposure mapping induces a unique pseudo-true outcome model. This model is the best approximation to the underlying potential outcomes that depends only on the user-chosen exposure. Utilizing that representation, the marginal policy effect admits a canonical decomposition into exposure-based direct and spillover effects, and each component provides its optimal approximation to the corresponding oracle objects that would be available if interference were fully known. We then focus on a setting that nests important empirical and theoretical applications in which both local network spillovers and global spillovers, such as market equilibrium, operate. There, the marginal policy effect further decomposes asymptotically into direct, local, and global channels. An important implication is that many existing methods are more robust than previously understood once we reinterpret their targets as channel-specific components of this pseudo-true policy estimand. Simulations and a semi-synthetic experiment calibrated to a large cash-transfer experiment show that these components can be recovered in realistic experimental designs.

We study nonparametric regression over Besov spaces from noisy observations under sub-exponential noise, aiming to achieve minimax-optimal guarantees on the integrated squared error that hold with high probability and adapt to the unknown noise level. To this end, we propose a wavelet-based online learning algorithm that dynamically adjusts to the observed gradient noise by adaptively clipping it at an appropriate level, eliminating the need to tune parameters such as the noise variance or gradient bounds. As a by-product of our analysis, we derive high-probability adaptive regret bounds that scale with the $\ell_1$-norm of the competitor. Finally, in the batch statistical setting, we obtain adaptive and minimax-optimal estimation rates for Besov spaces via a refined online-to-batch conversion. This approach carefully exploits the structure of the squared loss in combination with self-normalized concentration inequalities.

We introduce a novel cyclic Markov decision process (MDP) framework for multi-step decision problems with heterogeneous stage-specific dynamics, transitions, and discount factors across the cycle. In this setting, offline learning is challenging: optimizing a policy at any stage shifts the state distributions of subsequent stages, propagating mismatch across the cycle. To address this, we propose a modular structural framework that decomposes the cyclic process into stage-wise sub-problems. While generally applicable, we instantiate this principle as CycleFQI, an extension of fitted Q-iteration enabling theoretical analysis and interpretation. It uses a vector of stage-specific Q-functions, tailored to each stage, to capture within-stage sequences and transitions between stages. This modular design enables partial control, allowing some stages to be optimized while others follow predefined policies. We establish finite-sample suboptimality error bounds and derive global convergence rates under Besov regularity, demonstrating that CycleFQI mitigates the curse of dimensionality compared to monolithic baselines. Additionally, we propose a sieve-based method for asymptotic inference of optimal policy values under a margin condition. Experiments on simulated and real-world Type 1 Diabetes data sets demonstrate CycleFQI's effectiveness.