arXiv subjects

Jan Kobiolka

Publications and source records attributed to Jan Kobiolka.

4 recordsLinked to original sources

arXiv2026

Learning to Order: Task Sequencing as In-Context Optimization

Task sequencing (TS) is one of the core open problems in Deep Learning, arising in a plethora of real-world domains, from robotic assembly lines to autonomous driving. Unfortunately, prior work has not convincingly demonstrated the generalization ability of meta-learned TS methods to solve new TS problems, given few initial demonstrations. In this paper, we demonstrate that deep neural networks can meta-learn over an infinite prior of synthetically generated TS problems and achieve a few-shot generalization. We meta-learn a transformer-based architecture over datasets of sequencing trajectories generated from a prior distribution that samples sequencing problems as paths in directed graphs. In a large-scale experiment, we provide ample empirical evidence that our meta-learned models discover optimal task sequences significantly quicker than non-meta-learned baselines.

cs.LG↗

arXiv2026

POP: Prior-Fitted First-Order Optimization Policies

Gradient-based optimizers are highly sensitive to design choices in their adaptive learning rate mechanisms. To address this limitation, we introduce POP, a meta-learned Reinforcement Learning (RL) policy that predicts adaptive learning rates for gradient descent, conditioned on the contextual information provided in the optimization trajectory. Our method introduces a novel RL reward formulation, a new function-scaling strategy for in-distribution generalization, and a novel prior that is used to sample millions of synthetic optimization problems. We evaluate POP on an established benchmark including 43 optimization functions of various complexity, where it significantly outperforms gradient-based methods. Our evaluation demonstrates strong generalization capabilities without task-specific tuning.

cs.LG↗

arXiv2024

Lightweight Correlation-Aware Table Compression

The growing adoption of data lakes for managing relational data necessitates efficient, open storage formats that provide high scan performance and competitive compression ratios. While existing formats achieve fast scans through lightweight encoding techniques, they have reached a plateau in terms of minimizing storage footprint. Recently, correlation-aware compression schemes have been shown to reduce file sizes further. Yet, current approaches either incur significant scan overheads or require manual specification of correlations, limiting their practicability. We present $\texttt{Virtual}$, a framework that integrates seamlessly with existing open formats to automatically leverage data correlations, achieving substantial compression gains while having minimal scan performance overhead. Experiments on data-gov datasets show that $\texttt{Virtual}$ reduces file sizes by up to 40% compared to Apache Parquet.

cs.DB↗

arXiv2024

Reduced-order adaptive synchronization in a chaotic neural network with parameter mismatch: A dynamical system vs. machine learning approach

In this paper, we address the reduced-order synchronization problem between two chaotic memristive Hindmarsh-Rose (HR) neurons of different orders using two distinct methods. The first method employs the Lyapunov active control technique. Through this technique, we develop appropriate control functions to synchronize a 4D chaotic HR neuron (response system) with the canonical projection of a 5D chaotic HR neuron (drive system). Numerical simulations are provided to demonstrate the effectiveness of this approach. The second method is data-driven and leverages a machine learning-based control technique. Our technique utilizes an ad hoc combination of reservoir computing (RC) algorithms, incorporating reservoir observer (RO), online control (OC), and online predictive control (OPC) algorithms. We anticipate our effective heuristic RC adaptive control algorithm to guide the development of more formally structured and systematic, data-driven RC control approaches to chaotic synchronization problems, and to inspire more data-driven neuromorphic methods for controlling and achieving synchronization in chaotic neural networks in vivo.

nlin.AO↗