arXiv:2603.22339v3 Announce Type: replace-cross Abstract: Chinchilla Approach 2 is among the most widely used methods for fitting neural scaling laws. Its parabolic approximation introduces systematic biases in compute-optimal allocation estimates, even on noise-free synthetic data. Applied to published Llama 3 IsoFLOP data at open frontier compute scales, these biases imply a parameter underallocation corresponding to 6.5% of the $3.8times10^{25}$ FLOP training budget and $1.4M (90% CI: $412K-$2.9M) in unnecessary compute at 50% H100 MFU. Simulated multimodal model misallocations […]

Ver mais

arXiv:2603.10004v1 Announce Type: new Abstract: Clinical documentation can contain emotionally charged language with stigmatizing or privileging valences. We present a framework for detecting and classifying such language as stigmatizing, privileging, or neutral. We constructed a curated lexicon of biased terms scored for emotional valence. We then used lexicon-based matching to extract text chunks from OB-GYN delivery notes (Mount Sinai Hospital, NY) and MIMIC-IV discharge summaries across multiple specialties. Three clinicians annotated all chunks, enabling characterization of valence patterns […]

Ver mais

arXiv:2601.16314v1 Announce Type: new Abstract: Large language models (LLMs) enable rapid and consistent automated evaluation of open-ended exam responses, including dimensions of content and argumentation that have traditionally required human judgment. This is particularly important in cases where a large amount of exams need to be graded in a limited time frame, such as nation-wide graduation exams in various countries. Here, we examine the applicability of automated scoring on two large datasets of trial exam essays of two […]

Ver mais

arXiv:2603.01719v1 Announce Type: new Abstract: Conformal prediction (CP) provides finite-sample, distribution-free marginal coverage, but standard conformal regression intervals can be inefficient under heteroscedasticity and skewness. In particular, popular constructions such as conformalized quantile regression (CQR) often inherit a fixed notion of center and enforce equal-tailed errors, which can displace the interval away from high-density regions and produce unnecessarily wide sets. We propose Co-optimization for Adaptive Conformal Prediction (CoCP), a framework that learns prediction intervals by jointly optimizing a […]

Ver mais

The previous post talked about doing perfect shuffles: divide a deck in half, and alternately let one card from each half fall. It matters which half lets a card fall first. If the top half’s bottom card falls first, this is called an in-shuffle. If the bottom half’s bottom card falls first, it’s called an out-shuffle. With an out-shuffle, the top and bottom cards don’t move. Presumably it’s called an out-shuffle because the outside cards remain in place. […]

Ver mais

Hi all! New to this forum. I have interviewed at multiple places for quant-research role and actively job-searching as a new grad studying math/physics. I saw an opening for deepmind which seems one of the most interesting roles I’ve ever seen at intersection of physics math and ML. How hard is it to get an interview from them? I’m only ever applied for one other ML role which was fellow at anthropic and I didn’t get far in […]

Ver mais

arXiv:2603.26758v1 Announce Type: new Abstract: Distributed systems in which concurrent proposals are mutually exclusive face a fundamental stability constraint under network delay. In open systems where global state progression is event-driven rather than round-driven, propagation delay creates a conflict window within which overlapping proposals may generate competing branches. This paper derives a density-delay law for such exclusive state progression processes. Under independent proposal arrivals and bounded propagation delay, overlap is approximated by a Poisson model and fork depth […]

Ver mais

arXiv:2601.10874v1 Announce Type: new Abstract: We study d-way balanced allocation, which assigns each incoming job to the lightest loaded among d randomly chosen servers. While prior work has extensively studied the performance of the basic scheme, there has been less published work on adapting this technique to many aspects of large-scale systems. Based on our experience in building and running planet-scale cloud applications, we extend the understanding of d-way balanced allocation along the following dimensions: (i) Bursts: Events […]

Ver mais

Harnessing the predictive capability of Markov process models requires propagating probability density functions (beliefs) through the model. For many existing models however, belief propagation is analytically infeasible, requiring approximation or sampling to generate predictions. This paper proposes a functional modeling framework leveraging sparse Sum-of-Squares (SoS) forms for valid (conditional) density estimation. We study the theoretical restrictions of modeling conditional densities using the SoS form, and propose a novel functional form for addressing such limitations. The proposed architecture enables […]

Ver mais

Introduction It isn’t everyday that a company gets started based on one YouTube short. But I think that’s exactly what might happen to me after I watched this Alex Hormozi YouTube video and a while later, the idea clicked on September 1 2025. https://youtube.com/shorts/bn4N6z6MSIo?si=Qt2BbO-Q-ljehLsq&embedable=true The premise is simple: “The person asking the questions is the one closing (the deal)” – Alex Hormozi The thing was, I knew a little technical knowledge about Bitcoin. And I knew that there […]

Ver mais