Higher education institutions have historically relied on retrospective reporting to understand enrollment trends and student outcomes. Admissions offices scrutinized last year’s yield rates; registrars tracked semester-to-semester retention; academic affairs teams compiled graduation statistics after the fact. While these practices produced useful summaries, they offered no predictive leverage. By the time a pattern became visible in the static data, the window for meaningful intervention had almost always slammed shut. The current pivot toward predictive modeling isn’t just a technical […]

Ver mais

Deep neural networks are typically trained by uniformly sampling large datasets across epochs, despite evidence that not all samples contribute equally throughout learning. Recent work shows that progressively reducing the amount of training data can improve efficiency and generalization, but existing methods rely on fixed schedules that do not adapt during training. In this work, we propose Adaptive Data Dropout, a simple framework that dynamically adjusts the subset of training data based on performance feedback. Inspired by self-regulated […]

Ver mais

Prompting has a reputation for being “vibes-based.” You type something, the model replies, you tweak a sentence, it gets slightly better, and you keep nudging until it works—if it works. That’s fine for a weekend toy project. It’s a nightmare for anything serious: compliance text, data pipelines, code generation, or “please don’t embarrass me in front of the team” outputs. So here’s the upgrade: Prompt Reverse Engineering. It’s exactly what it sounds like: use the model’s wrong answer […]

Ver mais

We construct algorithms with optimal error for learning with adversarial noise. The overarching theme of this work is that the use of textsl{randomized} hypotheses can substantially improve upon the best error rates achievable with deterministic hypotheses. – For $η$-rate malicious noise, we show the optimal error is $frac{1}{2} cdot η/(1-η)$, improving on the optimal error of deterministic hypotheses by a factor of $1/2$. This answers an open question of Cesa-Bianchi et al. (JACM 1999) who showed randomness can […]

Ver mais

arXiv:2603.25923v1 Announce Type: new Abstract: Deep learning models have shown promise in EEG-based outcome prediction for comatose patients after cardiac arrest, but their reliability is often compromised by subtle forms of data leakage. In particular, when long EEG recordings are segmented into short windows and reused across multiple training stages, models may implicitly encode and propagate label information, leading to overly optimistic validation performance and poor generalization. In this study, we identify a previously overlooked form of data […]

Ver mais

arXiv:2510.12026v3 Announce Type: replace-cross Abstract: Mamba, a recently proposed linear-time sequence model, has attracted significant attention for its computational efficiency and strong empirical performance. However, a rigorous theoretical understanding of its underlying mechanisms remains limited. In this work, we provide a theoretical analysis of Mamba’s in-context learning (ICL) capability by focusing on tasks defined by low-dimensional nonlinear target functions. Specifically, we study in-context learning of a single-index model $y approx g_*(langle boldsymbol{beta}, boldsymbol{x} rangle)$, which depends on only […]

Ver mais

arXiv:2602.13362v1 Announce Type: new Abstract: A key challenge in probabilistic regression is ensuring that predictive distributions accurately reflect true empirical uncertainty. Minimizing overall prediction error often encourages models to prioritize informativeness over calibration, producing narrow but overconfident predictions. However, in safety-critical settings, trustworthy uncertainty estimates are often more valuable than narrow intervals. Realizing the problem, several recent works have focused on post-hoc corrections; however, existing methods either rely on weak notions of calibration (such as PIT uniformity) or […]

Ver mais

arXiv:2602.02520v1 Announce Type: new Abstract: AI technology development has transformed the field of engineering education with its adaptivity-driven, data-based, and ethical-led learning platforms that promote equity, diversity, and inclusivity. But with so much progress being made in so many areas, there are unfortunately gaps in gender equity, representation in cultures around the world, and access to education and jobs in stem education. The paper describes an ethical approach to using AI technology that supports the United Nations 2030 […]

Ver mais