technocracy

arXiv:2605.00581v1 Announce Type: new Abstract: Gradient Boosting Decision Trees (GBDTs) dominate tabular machine learning, with modern implementations like XGBoost, LightGBM, and CatBoost being based on Newton boosting: a second-order descent step in the space of decision trees. Despite its empirical success, the global convergence of Newton boosting is poorly understood compared to first-order boosting. In this paper, we introduce Restricted Newton Descent, which studies convex optimization with Newton’s method on Hilbert spaces with inexact iterates, based on the […]

Ver mais

We study reinforcement learning for revenue management with delayed feedback, where a substantial fraction of value is determined by customer cancellations and modifications observed days after booking. We propose emph{choice-model-assisted RL}: a calibrated discrete choice model is used as a fixed partial world model to impute the delayed component of the learning target at decision time. In the fixed-model deployment regime, we prove that tabular Q-learning with model-imputed targets converges to an $O(varepsilon/(1-γ))$ neighborhood of the optimal Q-function, […]

Ver mais

arXiv:2604.06260v1 Announce Type: new Abstract: Test-time scaling investigates whether a fixed diffusion language model (DLM) can generate better outputs when given more inference compute, without additional training. However, naive best-of-$K$ sampling is fundamentally limited because it repeatedly draws from the same base diffusion distribution, whose high-probability regions are often misaligned with high-quality outputs. We propose $S^3$ (Stratified Scaling Search), a classical verifier-guided search method that improves generation by reallocating compute during the denoising process rather than only at […]

Ver mais

Since I felt like I was relying on Claude Code a lot recently, I wanted to see how hard it is to implement a diffusion language model from scratch without the help of AI-Generated code. So I built one while waiting for the training for my master’s thesis. This is what I got after a few hours of training on my MacBook Air M2. I trained on the tiny Shakespeare dataset from Karpathy and prompted “to be, “ […]

Ver mais

arXiv:2603.24652v1 Announce Type: new Abstract: Network pruning, which removes less important parameters or architectures, is often expected to improve efficiency while preserving performance. However, this expectation does not consistently hold across language tasks: pruned models can perform well on non-generative tasks but frequently fail in generative settings. To understand this discrepancy, we analyze network pruning from a representation-hierarchy perspective, decomposing the internal computation of language models into three sequential spaces: embedding (hidden representations), logit (pre-softmax outputs), and probability […]

Ver mais

arXiv:2603.24801v1 Announce Type: new Abstract: Computed tomography image segmentation of complex abdominal aortic aneurysms (AAA) often fails because the models assign internal focus to irrelevant structures or do not focus on thin, low-contrast targets. Where the model looks is the primary training signal, and thus we propose an Explainable AI (XAI) guided encoder shaping framework. Our method computes a dense, attribution-based encoder focus map (“XAI field”) from the final encoder block and uses it in two complementary ways: […]

Ver mais

:::info Authors: Janice Lan Aini Palizhati Muhammed Shuaibi Brandon M. Wood Brook Wander Abhishek Das Matt Uyttendaele C. Lawrence Zitnick Zachary W. Ulissi ::: Abstract Computational catalysis is playing an increasingly significant role in the design of catalysts across a wide range of applications. A common task for many computational methods is the need to accurately compute the adsorption energy for an adsorbate and a catalyst surface of interest. Traditionally, the identification of low-energy adsorbate-surface configurations relies on […]

Ver mais

arXiv:2603.23302v1 Announce Type: cross Abstract: We study nonparametric covariance function estimation for functional data observed with noise at discrete locations on a $d$-dimensional domain. Estimating the covariance function from discretely observed data is a challenging nonparametric problem, particularly in multidimensional settings, since the covariance function is defined on a product domain and thus suffers from the curse of dimensionality. This motivates the use of adaptive estimators, such as deep learning estimators. However, existing theoretical results are largely limited […]

Ver mais