All computational procedures were performed either on a desktop workstation running Ubuntu 18.04 By minimising off-target activation, Bayesian target optimisation could enable (e.g.) Here we provide further mathematical details for optimising holographic stimuli. Next we must evaluate the partial derivative on the right-hand side of Equation 13. The covariance between a GP and its derivative is given by [40, Sec 9.4] Simulations consisted of both ORF mapping and stimulus optimisation phases. For reference, a typical ORF mean function is given in Figure S2.

The recruitment website is jazzy, awash with pictures of happy young workers, and festooned with upbeat mini-slogans such as insane speed, infinite curiosity and customer obsession. Read a bit lower, and there are promises of perks galore: competitive compensation, free meals, free gym membership, free health and dental care and so on. But then comes the catch. Each job ad contains a warning: Please don't join if you're not excited about working ~70 hrs/week in person with some of the most ambitious people in NYC. The website belongs to Rilla, a New York-based tech business which sells AI-based systems that allow employers to monitor sales representatives when they are out and about, interacting with clients. The company has become something of a poster child for a fast-paced workplace culture known as 996, also sometimes referred to as hustle culture or grindcore.

Performative predictions influence the very outcomes they aim to forecast. We study performative predictions that affect a sample (e.g., only existing users of an app) and/or the whole population (e.g., all potential app users). This raises the question of how well models generalize under performativity. For example, how well can we draw insights about new app users based on existing users when both of them react to the app's predictions? We address this question by embedding performative predictions into statistical learning theory. We prove generalization bounds under performative effects on the sample, on the population, and on both. A key intuition behind our proofs is that in the worst case, the population negates predictions, while the sample deceptively fulfills them. We cast such self-negating and self-fulfilling predictions as min-max and min-min risk functionals in Wasserstein space, respectively. Our analysis reveals a fundamental trade-off between performatively changing the world and learning from it: the more a model affects data, the less it can learn from it. Moreover, our analysis results in a surprising insight on how to improve generalization guarantees by retraining on performatively distorted samples. We illustrate our bounds in a case study on prediction-informed assignments of unemployed German residents to job trainings, drawing upon administrative labor market records from 1975 to 2017 in Germany.

Techniques for feedforward networks (FFNs) and convolutional networks (CNNs) are frequently reused across families, but the relationship between the underlying model classes is rarely made explicit. We introduce a unified node-level formalization with tensor-valued activations and show that generalized feedforward networks form a strict subset of generalized convolutional networks. Motivated by the mismatch in per-input parameterization between the two families, we propose model projection, a parameter-efficient transfer learning method for CNNs that freezes pretrained per-input-channel filters and learns a single scalar gate for each (output channel, input channel) contribution. Projection keeps all convolutional layers adaptable to downstream tasks while substantially reducing the number of trained parameters in convolutional layers. We prove that projected nodes take the generalized FFN form, enabling projected CNNs to inherit feedforward techniques that do not rely on homogeneous layer inputs. Experiments across multiple ImageNet-pretrained backbones and several downstream image classification datasets show that model projection is a strong transfer learning baseline under simple training recipes.

Multicalibration gradient boosting has recently emerged as a scalable method that empirically produces approximately multicalibrated predictors and has been deployed at web scale. Despite this empirical success, its convergence properties are not well understood. In this paper, we bridge the gap by providing convergence guarantees for multicalibration gradient boosting in regression with squared-error loss. We show that the magnitude of successive prediction updates decays at $O(1/\sqrt{T})$, which implies the same convergence rate bound for the multicalibration error over rounds. Under additional smoothness assumptions on the weak learners, this rate improves to linear convergence. We further analyze adaptive variants, showing local quadratic convergence of the training loss, and we study rescaling schemes that preserve convergence. Experiments on real-world datasets support our theory and clarify the regimes in which the method achieves fast convergence and strong multicalibration.

Standard chain-of-thought reasoning generates a solution in a single forward pass, committing irrevocably to each token and lacking a mechanism to recover from early errors. We introduce Inference-Time Rethinking, a generative framework that enables iterative self-correction by decoupling declarative latent thought vectors from procedural generation. We factorize reasoning into a continuous latent thought vector (what to reason about) and a decoder that verbalizes the trace conditioned on this vector (how to reason). Beyond serving as a declarative buffer, latent thought vectors compress the reasoning structure into a continuous representation that abstracts away surface-level token variability, making gradient-based optimization over reasoning strategies well-posed. Our prior model maps unstructured noise to a learned manifold of valid reasoning patterns, and at test time we employ a Gibbs-style procedure that alternates between generating a candidate trace and optimizing the latent vector to better explain that trace, effectively navigating the latent manifold to refine the reasoning strategy. Training a 0.2B-parameter model from scratch on GSM8K, our method with 30 rethinking iterations surpasses baselines with 10 to 15 times more parameters, including a 3B counterpart. This result demonstrates that effective mathematical reasoning can emerge from sophisticated inference-time computation rather than solely from massive parameter counts.

Accurate imputation of missing data is critical to downstream machine learning performance. We formulate missing data imputation as a risk minimisation problem, which highlights a covariate shift between the observed and unobserved data distributions. This covariate shift induced bias is not accounted for by popular imputation methods and leads to suboptimal performance. In this paper, we derive theoretically valid importance weights that correct for the induced distributional bias. Furthermore, we propose a novel imputation algorithm that jointly estimates both the importance weights and imputation models, enabling bias correction throughout the imputation process. Empirical results across benchmark datasets show reductions in root mean squared error and Wasserstein distance of up to 7% and 20%, respectively, compared to otherwise identical unweighted methods.