arXiv subjects

Jason Zhu

Publications and source records attributed to Jason Zhu.

6 recordsLinked to original sources

arXiv2026

Computation of Strong Solutions to Stochastic Variational Inequalities

This paper studies the computation of strong solutions of monotone variational inequalities (VIs) with Lipschitz continuous operators. Building on the idea of accumulative regularization, we develop a general framework for VIs, with particular emphasis on stochastic settings. Under unbiased stochastic oracles with uniformly bounded variance $ \sigma^2$, AR computes an approximate solution with expected operator residual bounded by $\varepsilon$ using at most $ \widetilde{O}\left(\tfrac{LD_0}{\varepsilon}+\tfrac{ \sigma^2}{\varepsilon^2}(\log\tfrac{LD_0}{\varepsilon})^3\right) $ stochastic oracle calls, where $L$ is the Lipschitz constant and $D_0$ bounds the initial distance to the solution. It substantially improves the existing $\mathcal{O}( \sigma^2/\varepsilon^4)$ complexity for residual reduction and matches the lower bound up to logarithmic factors. For strongly monotone VIs, measured by the distance to the solution, AR achieves the optimal oracle complexity when the strong monotonicity modulus is known. By treating the problem as merely monotone, AR still achieves nearly optimal complexity without knowledge of this modulus. We further introduce a state-dependent noise model applicable to general monotone VIs with potentially nonunique solutions, extending state-dependent noise analysis beyond the strongly monotone setting. Under this model, AR, when equipped with an enhanced stochastic operator extrapolation (SOE) method, achieves nearly optimal complexity with the stochastic term depending on the variance at a solution.

math.OC↗

arXiv2026

AdMem: Advanced Memory for Task-solving Agents

Large Language Models (LLMs) show promise as tool-using agents but remain limited in long-horizon tasks that require remembering, organizing, and reusing knowledge. Prior memory approaches aim to resolve the situation, but mainly focus on storing factual information. Recent work on procedural memory improves task reuse, yet often reduces to replaying past successes without addressing failure cases or online scalability. We introduce a unified and automatic memory framework that integrates semantic, episodic, and procedural memory in a bi-level design combining short-term and long-term stores. A multi-agent architecture with actor, memory, and critic agents enables automatic memory generation, reward annotation, and adaptive retrieval. Long-term memory is managed through reward-based evaluation, merging, and pruning, ensuring scalability and continual improvement. Experiments across various environments show that our approach improves robustness and success on long multi-turn tasks compared to existing baselines. This work highlights the importance of comprehensive, adaptive memory for advancing LLM-based agents.

cs.AI↗

arXiv2025

Towards Concise and Adaptive Thinking in Large Reasoning Models: A Survey

Large reasoning models (LRMs) like OpenAI o1 and DeepSeek R1 have demonstrated impressive performance on complex reasoning tasks like mathematics and programming with long Chain-of-Thought (CoT) reasoning sequences (slow-thinking), compared with traditional large language models (fast-thinking). However, these reasoning models also face a huge challenge that generating unnecessarily lengthy and redundant reasoning chains even for trivial questions. This phenomenon leads to a significant waste of inference resources, increases the response time for simple queries, and hinders the practical application of LRMs in real-world products. To this end, it is crucial to shorten lengthy reasoning chains and learn adaptive reasoning between fast and slow thinking based on input difficulty. In this survey, we provide a comprehensive overview of recent progress in concise and adaptive thinking for efficient reasoning of LRMs, including methodologies, benchmarks, and challenges for future exploration. We hope this survey can help researchers quickly understand the landscape of this field and inspire novel adaptive thinking ideas to facilitate better usage of LRMs.

cs.AI↗

arXiv2023

Data Depth and Core-based Trend Detection on Blockchain Transaction Networks

Blockchains are significantly easing trade finance, with billions of dollars worth of assets being transacted daily. However, analyzing these networks remains challenging due to the sheer volume and complexity of the data. We introduce a method named InnerCore that detects market manipulators within blockchain-based networks and offers a sentiment indicator for these networks. This is achieved through data depth-based core decomposition and centered motif discovery, ensuring scalability. InnerCore is a computationally efficient, unsupervised approach suitable for analyzing large temporal graphs. We demonstrate its effectiveness by analyzing and detecting three recent real-world incidents from our datasets: the catastrophic collapse of LunaTerra, the Proof-of-Stake switch of Ethereum, and the temporary peg loss of USDC - while also verifying our results against external ground truth. Our experiments show that InnerCore can match the qualified analysis accurately without human involvement, automating blockchain analysis in a scalable manner, while being more effective and efficient than baselines and state-of-the-art attributed change detection approach in dynamic graphs.

cs.LG↗

arXiv2022

On False Data Injection Attack against Building Automation Systems

KNX is one popular communication protocol for a building automation system (BAS). However, its lack of security makes it subject to a variety of attacks. We are the first to study the false data injection attack against a KNX based BAS. We design a man-in-the-middle (MITM) attack to change the data from a temperature sensor and inject false data into the BAS. We model a BAS and analyze the impact of the false data injection attack on the system in terms of energy cost. Since the MITM attack may disturb the KNX traffic, we design a machine learning (ML) based detection strategy to detect the false data injection attack using a novel feature based on the Jensen Shannon Divergence (JSD), which measures the similarity of KNX telegram inter-arrival time distributions with attack and with no attack. We perform real-world experiments and validate the presented false data injection attack and the ML based detection strategy. We also simulate a BAS, and show that the false data injection attack has a huge impact on the BAS in terms of power consumption.

cs.CR↗

arXiv2019

Deep Learning in Asset Pricing

We use deep neural networks to estimate an asset pricing model for individual stock returns that takes advantage of the vast amount of conditioning information, while keeping a fully flexible form and accounting for time-variation. The key innovations are to use the fundamental no-arbitrage condition as criterion function, to construct the most informative test assets with an adversarial approach and to extract the states of the economy from many macroeconomic time series. Our asset pricing model outperforms out-of-sample all benchmark approaches in terms of Sharpe ratio, explained variation and pricing errors and identifies the key factors that drive asset prices.

q-fin.ST↗