We introduce a variational inference framework for training the Gaussian process latent variable model and thus performing Bayesian nonlinear dimensionality reduction. This method allows us to variationally integrate out the input variables of the Gaussian process and compute a lower bound on the exact marginal likelihood of the nonlinear latent variable model. The maximization of the variational lower bound provides a Bayesian training procedure that is robust to overfitting and can automatically select the dimensionality of the nonlinear […]

Ver mais

Atlassian laid off 10% of its workforce, around 1,600 people, as the company looks to funnel more funds to AI.

Ver mais

arXiv:2602.17791v1 Announce Type: new Abstract: Large language models (LLMs) have become popular writing tools among students and may expand access to high-quality feedback for students with less access to traditional writing support. At the same time, LLMs may standardize student voice or invite overreliance. This study examines how adoption of LLM-assisted writing varies across socioeconomic groups and how it relates to outcomes in a high-stakes context: U.S. college admissions. We analyze a de-identified longitudinal dataset of applications to […]

Ver mais

arXiv:2601.20269v2 Announce Type: replace Abstract: Machine learning models in high-stakes applications, such as recidivism prediction and automated personnel selection, often exhibit systematic performance disparities across sensitive subpopulations, raising critical concerns regarding algorithmic bias. Fairness auditing addresses these risks through two primary functions: certification, which verifies adherence to fairness constraints; and flagging, which isolates specific demographic groups experiencing disparate treatment. However, existing auditing techniques are frequently limited by restrictive distributional assumptions or prohibitive computational overhead. We propose a novel […]

Ver mais

Tear film (TF) breakup is a key driver of understanding dry eye disease, yet estimating TF thickness and osmolarity from fluorescence (FL) imaging typically requires solving computationally expensive inverse problems. We propose an operator learning framework that replaces traditional inverse solvers with neural operators trained on simulated TF dynamics. This approach offers a scalable path toward rapid, data-driven analysis of tear film dynamics.

Ver mais

arXiv:2603.08558v1 Announce Type: cross Abstract: Learning compact state representations in Markov Decision Processes (MDPs) has proven crucial for addressing the curse of dimensionality in large-scale reinforcement learning (RL) problems. Existing principled approaches leverage structural priors on the MDP by constructing state representations as linear combinations of the state-graph Laplacian eigenvectors. When the transition graph is unknown or the state space is prohibitively large, the graph spectral features can be estimated directly via sample trajectories. In this work, we […]

Ver mais

Preliminaries Bayesian Theorem Bayesian Model Averaging(BMA)1 Bayesian model averaging(BMA) is another wildly used method that is very like a combining model. However, the difference between BMA and combining models is also significant. A Bayesian model averaging is a Bayesian formula in which the random variable are models(hypothesizes) (h=1,2,cdots,H) with prior probability (Pr(h)), then the marginal distribution over data (X) is: [ Pr(X)=sum_{h=1}^{H}Pr(X|h)Pr(h) ] And the MBA is used to select a model(hypothesis) that can model the data best […]

Ver mais

I’ve spent some time recently building an RL agent to play competitive Pokémon (Generation 9 Random Battles on Pokémon Showdown). I wanted to share the architecture, the training pipeline, and some thoughts on the MCTS vs. pure-network approaches in this specific environment. Why Pokémon? From an RL perspective, a Pokémon battle is a great proxy for real-world, messy decision-making. It combines three massive headaches: Simultaneous Action: Both agents lock in actions concurrently. You are trying to approximate Nash […]

Ver mais

With reports that the ChatGPT owner OpenAI is eyeing an initial public offering (IPO) in the second half of 2026, in what could be the largest debut of all time, it’s worth looking at what the artificial intelligence leader could bring to Wall Street. Although CEO Sam Altman has remained noncommittal when it comes to unveiling his intentions towards going public this year, there have been reports that OpenAI could look to debut at a valuation of $1 […]

Ver mais