Differentially private federated learning (DP-FL) enables clients to collaboratively train machine learning models while preserving the privacy of their local data. However, most existing DP-FL approaches assume that all clients share a uniform privacy budget, an assumption that does not hold in real-world scenarios where privacy requirements vary widely. This privacy heterogeneity poses a significant challenge: conventional client selection strategies, which typically rely on data quantity, cannot distinguish between clients providing high-quality updates and those introducing substantial noise […]

Ver mais

The next generation of autonomous agents must not only learn efficiently but also act reliably and adapt their behavior in open worlds. Standard approaches typically assume fixed tasks and environments with little or no novelty, which limits world models’ ability to support agents that must evolve their policies as conditions change. This paper outlines a vision for foundation world models: persistent, compositional representations that unify reinforcement learning, reactive/program synthesis, and abstraction mechanisms. We propose an agenda built around […]

Ver mais

arXiv:2601.16249v1 Announce Type: new Abstract: Learning DAG structures from purely observational data remains a long-standing challenge across scientific domains. An emerging line of research leverages the score of the data distribution to initially identify a topological order of the underlying DAG via leaf node detection and subsequently performs edge pruning for graph recovery. This paper extends the score matching framework for causal discovery, which is originally designated for continuous data, and introduces a novel leaf discriminant criterion based […]

Ver mais

arXiv:2604.01378v1 Announce Type: new Abstract: Offline reinforcement learning (RL) has received increasing attention for learning policies from previously collected data without interaction with the real environment, which is particularly important in high-stakes applications. While a growing body of work has developed offline RL algorithms, these methods often rely on restrictive assumptions about data coverage and suffer from distribution shift. In this paper, we propose a residuals-based offline RL framework for general state and action spaces. Specifically, we define […]

Ver mais

If you’ve glanced at a tech news feed anytime in the last year, you’ve likely felt the collective heart palpitations of the software development industry. Headlines scream about the “End of the Programmer” showcasing tools like Devin, GitHub Copilot and Cursor churning out entire web apps from a single text prompt It’s easy to fall into a spiral of existential dread. Will a neural network render your hard-earned computer science degree or boot camp certificate obsolete? Take a deep breath. […]

Ver mais

:::info Astounding Stories of Super-Science March, 1932, by Astounding Stories is part of HackerNoon’s Book Blog Post series. You can jump to any chapter in this book here. The Affair of the Brains – Chapter IX: The Brain Speaks Astounding Stories of Super-Science March 1932: The Affair of the Brains – Chapter IX The Brain Speaks By Anthony Gilmore ::: A case lay revealed. At first, while it was unlit, it seemed nothing more than that: a case like those glass-sided […]

Ver mais

We study model-based learning of finite-window policies in tabular partially observable Markov decision processes (POMDPs). A common approach to learning under partial observability is to approximate unbounded history dependencies using finite action-observation windows. This induces a finite-state Markov decision process (MDP) over histories, referred to as the superstate MDP. Once a model of this superstate MDP is available, standard MDP algorithms can be used to compute optimal policies, motivating the need for sample-efficient model estimation. Estimating the superstate […]

Ver mais

arXiv:2601.23030v1 Announce Type: new Abstract: Inference in non-linear continuous stochastic processes on trees is challenging, particularly when observations are sparse (leaf-only) and the topology is complex. Exact smoothing via Doob’s $h$-transform is intractable for general non-linear dynamics, while particle-based methods degrade in high dimensions. We propose Neural Backward Filtering Forward Guiding (NBFFG), a unified framework for both discrete transitions and continuous diffusions. Our method constructs a variational posterior by leveraging an auxiliary linear-Gaussian process. This auxiliary process yields […]

Ver mais

Questions for developers: “What’s the one area you’re afraid to touch?” “When’s the last time you deployed on a Friday?” “What broke in production in the last 90 days that wasn’t caught by tests?” Questions for the CTO/EM: “What feature has been blocked for over a year?” “Do you have real-time error visibility right now?” “What was the last feature that took significantly longer than estimated?” Questions for business stakeholders: “Are there features that got quietly turned off […]

Ver mais