arXiv subjects

Qi Deng

Publications and source records attributed to Qi Deng.

At least 19 recordsLinked to original sources

arXiv2026

Agentopia: Long-Term Life Simulation and Learning in Agent Societies

Humans learn from social life. Simulating this process with LLM-powered agents represents a promising research direction, raising a natural question: whether LLMs can learn from such simulated social experience to better understand and replicate human behavior. However, prior agent society simulations typically operate at the scale of days, limiting the depth of social interactions and long-term growth. In this paper, we study long-term life simulation and LLM learning in agent societies, with two goals: (1) investigating social behaviors that emerge from life-long simulation, and (2) developing anthropomorphic capabilities in LLMs, particularly intelligence in social life, through years of simulated social experience. Specifically, we present Agentopia, a comprehensive framework for long-term life simulation in multi-agent societies, where 100 agents autonomously pursue personal growth, develop social relationships, and fulfill their needs and goals over 10 simulated years. We define life reward to mirror human well-being, and leverage this reward to train LLMs via rejection sampling. Extensive experiments show that agents exhibit rich emergent social behaviors. Furthermore, life reward training effectively enhances the underlying LLM, which leads to improved agent well-being in simulation, and generalizes to downstream role-playing benchmarks with +15.6% improvement.

cs.CL↗

arXiv2026

ZOTTA: Test-Time Adaptation with Gradient-Free Zeroth-Order Optimization

Test-time adaptation (TTA) aims to improve model robustness under distribution shifts by adapting to unlabeled test data, but most existing methods rely on backpropagation (BP), which is computationally costly and incompatible with non-differentiable models such as quantized models, limiting practical deployment on numerous edge devices. Recent BP-free approaches alleviate overhead but remain either architecture-specific or limited in optimization capacity to handle high-dimensional models. We propose ZOTTA, a fully BP-free TTA framework that performs efficient adaptation using only forward passes via Zeroth-Order Optimization (ZOO). While ZOO is theoretically appealing, naive application leads to slow convergence under high-dimensional parameter spaces and unstable optimization due to the lack of labels. ZOTTA overcomes these challenges through 1) Distribution-Robust Layer Selection, which automatically identifies and freezes layers that already extract distribution-invariant features, updating only domain-sensitive layers to reduce the optimization dimensionality and accelerate convergence; 2) Spatial Feature Aggregation Alignment, which stabilizes ZOO by aligning globally aggregated spatial features between source and target to reduce gradient variance. Together, these components enable architecture-agnostic and stable BP-free adaptation. Extensive experiments on ImageNet-C/R/Sketch/A show that ZOTTA outperforms or matches BP-based methods, e.g., it reduces memory usage by 84% and improves accuracy by 3.9% over SAR on ImageNet-C. Code:https://github.com/Zhang-Ronghao/zotta.

cs.CV↗

arXiv2026

A Penalty Approach for Differentiation Through Black-Box Quadratic Programming Solvers

Differentiating through the solution of a quadratic program (QP) is a central problem in differentiable optimization. Most existing approaches differentiate through the Karush--Kuhn--Tucker (KKT) system, but their computational cost and numerical robustness can degrade at scale. To address these limitations, we propose dXPP, a penalty-based differentiation framework that decouples QP solving from differentiation. In the solving step (forward pass), dXPP is solver-agnostic and can leverage any black-box QP solver. In the differentiation step (backward pass), we map the solution to a smooth approximate penalty problem and implicitly differentiate through it, requiring only the solution of a much smaller linear system in the primal variables. This approach bypasses the difficulties inherent in explicit KKT differentiation and significantly improves computational efficiency and robustness. We evaluate dXPP on various tasks, including randomly generated QPs, large-scale sparse projection problems, and a real-world multi-period portfolio optimization task. Empirical results demonstrate that dXPP is competitive with KKT-based differentiation methods and achieves substantial speedups on large-scale problems. Our implementation is open source and available at https://github.com/mmmmmmlinghu/dXPP.

cs.LG↗

arXiv2025

Integrated Prediction and Multi-period Portfolio Optimization

Multi-period portfolio optimization is important for real portfolio management, as it accounts for transaction costs, path-dependent risks, and the intertemporal structure of trading decisions that single-period models cannot capture. Classical methods usually follow a two-stage framework: machine learning algorithms are employed to produce forecasts that closely fit the realized returns, and the predicted values are then used in a downstream portfolio optimization problem to determine the asset weights. This separation leads to a fundamental misalignment between predictions and decision outcomes, while also ignoring the impact of transaction costs. To bridge this gap, recent studies have proposed the idea of end-to-end learning, integrating the two stages into a single pipeline. This paper introduces IPMO (Integrated Prediction and Multi-period Portfolio Optimization), a model for multi-period mean-variance portfolio optimization with turnover penalties. The predictor generates multi-period return forecasts that parameterize a differentiable convex optimization layer, which in turn drives learning via portfolio performance. For scalability, we introduce a mirror-descent fixed-point (MDFP) differentiation scheme that avoids factorizing the Karush-Kuhn-Tucker (KKT) systems, which thus yields stable implicit gradients and nearly scale-insensitive runtime as the decision horizon grows. In experiments with real market data and two representative time-series prediction models, the IPMO method consistently outperforms the two-stage benchmarks in risk-adjusted performance net of transaction costs and achieves more coherent allocation paths. Our results show that integrating machine learning prediction with optimization in the multi-period setting improves financial outcomes and remains computationally tractable.

cs.CE↗

arXiv2025

A Smooth Approximation Framework for Weakly Convex Optimization

Standard complexity analyses for weakly convex optimization rely on the Moreau envelope technique proposed by Davis and Drusvyatskiy (2019). The main insight is that nonsmooth algorithms, such as proximal subgradient, proximal point, and their stochastic variants, implicitly minimize a smooth surrogate function induced by the Moreau envelope. Meanwhile, explicit smoothing, which directly minimizes a smooth approximation of the objective, has long been recognized as an efficient strategy for nonsmooth optimization. In this paper, we generalize the notion of smoothable functions, which was proposed by Beck and Teboulle (2012) for nonsmooth convex optimization. This generalization provides a unified viewpoint on several important smoothing techniques for weakly convex optimization, including Nesterov-type smoothing and Moreau envelope smoothing. Our theory yields a framework for designing smooth approximation algorithms for both deterministic and stochastic weakly convex problems with provable complexity guarantees. Furthermore, our theory extends to the smooth approximation of non-Lipschitz functions, allowing for complexity analysis even when global Lipschitz continuity does not hold.

math.OC↗

arXiv2025

Accelerated Distance-adaptive Methods for H\"{o}lder Smooth and Convex Optimization

This paper introduces new parameter-free first-order methods for convex optimization problems in which the objective function exhibits H\"{o}lder smoothness. Inspired by the recently proposed distance-over-gradient (DOG) technique, we propose an accelerated distance-adaptive method which achieves optimal anytime convergence rates for H\"{o}lder smooth problems without requiring prior knowledge of smoothness parameters or explicit parameter tuning. Importantly, our parameter-free approach removes the necessity of specifying target accuracy in advance, addressing a limitation found in the universal fast gradient methods (Nesterov, Yu. \textit{Mathematical Programming}, 2015). For convex stochastic optimization, we further present a parameter-free accelerated method that eliminates the need for line-search procedures. Preliminary experimental results highlight the effectiveness of our approach on convex nonsmooth problems and its advantages over existing parameter-free or accelerated methods.

math.OC↗

arXiv2025

A Confidence-Constrained Cloud-Edge Collaborative Framework for Autism Spectrum Disorder Diagnosis

Autism Spectrum Disorder (ASD) diagnosis systems in school environments increasingly relies on IoT-enabled cameras, yet pure cloud processing raises privacy and latency concerns while pure edge inference suffers from limited accuracy. We propose Confidence-Constrained Cloud-Edge Knowledge Distillation (C3EKD), a hierarchical framework that performs most inference at the edge and selectively uploads only low-confidence samples to the cloud. The cloud produces temperature-scaled soft labels and distils them back to edge models via a global loss aggregated across participating schools, improving generalization without centralizing raw data. On two public ASD facial-image datasets, the proposed framework achieves a superior accuracy of 87.4\%, demonstrating its potential for scalable deployment in real-world applications.

cs.NI↗

arXiv2025

Revisiting Randomized Smoothing: Nonsmooth Nonconvex Optimization Beyond Global Lipschitz Continuity

Randomized smoothing is a widely adopted technique for optimizing nonsmooth objective functions. However, its efficiency analysis typically relies on global Lipschitz continuity, a condition rarely met in practical applications. To address this limitation, we introduce a new subgradient growth condition that naturally encompasses a wide range of locally Lipschitz functions, with the classical global Lipschitz function as a special case. Under this milder condition, we prove that randomized smoothing yields a differentiable function that satisfies certain generalized smoothness properties. To optimize such functions, we propose novel randomized smoothing gradient algorithms that, with high probability, converge to $(\delta, \epsilon)$-Goldstein stationary points and achieve a sample complexity of $\tilde{\mathcal{O}}(d^{5/2}\delta^{-1}\epsilon^{-4})$. By incorporating variance reduction techniques, we further improve the sample complexity to $\tilde{\mathcal{O}}(d^{3/2}\delta^{-1}\epsilon^{-3})$, matching the optimal $\epsilon$-bound under the global Lipschitz assumption, up to a logarithmic factor. Experimental results validate the effectiveness of our proposed algorithms.

math.OC↗

arXiv2025

Exploring Audio Cues for Enhanced Test-Time Video Model Adaptation

Test-time adaptation (TTA) aims to boost the generalization capability of a trained model by conducting self-/unsupervised learning during the testing phase. While most existing TTA methods for video primarily utilize visual supervisory signals, they often overlook the potential contribution of inherent audio data. To address this gap, we propose a novel approach that incorporates audio information into video TTA. Our method capitalizes on the rich semantic content of audio to generate audio-assisted pseudo-labels, a new concept in the context of video TTA. Specifically, we propose an audio-to-video label mapping method by first employing pre-trained audio models to classify audio signals extracted from videos and then mapping the audio-based predictions to video label spaces through large language models, thereby establishing a connection between the audio categories and video labels. To effectively leverage the generated pseudo-labels, we present a flexible adaptation cycle that determines the optimal number of adaptation iterations for each sample, based on changes in loss and consistency across different views. This enables a customized adaptation process for each sample. Experimental results on two widely used datasets (UCF101-C and Kinetics-Sounds-C), as well as on two newly constructed audio-video TTA datasets (AVE-C and AVMIT-C) with various corruption types, demonstrate the superiority of our approach. Our method consistently improves adaptation performance across different video classification models and represents a significant step forward in integrating audio information into video TTA. Code: https://github.com/keikeiqi/Audio-Assisted-TTA.

cs.CV↗

arXiv2025

BenLOC: A Benchmark for Learning to Configure MIP Optimizers

The automatic configuration of Mixed-Integer Programming (MIP) optimizers has become increasingly critical as the large number of configurations can significantly affect solver performance. Yet the lack of standardized evaluation frameworks has led to data leakage and over-optimistic claims, as prior studies often rely on homogeneous datasets and inconsistent experimental setups. To promote a fair evaluation process, we present BenLOC, a comprehensive benchmark and open-source toolkit, which not only offers an end-to-end pipeline for learning instance-wise MIP optimizer configurations, but also standardizes dataset selection, train-test splits, feature engineering and baseline choice for unbiased and comprehensive evaluations. Leveraging this framework, we conduct an empirical analysis on five well-established MIP datasets and compare classical machine learning models with handcrafted features against state-of-the-art deep-learning techniques. The results demonstrate the importance of datasets, features and baseline criteria proposed by BenLOC and the effectiveness of BenLOC in providing unbiased and comprehensive evaluations.

math.OC↗

arXiv2025

Liquidity-adjusted Return and Volatility, and Autoregressive Models

We construct liquidity-adjusted return and volatility using purposely designed liquidity metrics (liquidity jump and liquidity diffusion) that incorporate additional liquidity information. Based on these measures, we introduce a liquidity-adjusted ARMA-GARCH framework to address the limitations of traditional ARMA-GARCH models, which are not effectively in modeling illiquid assets with high liquidity variability, such as cryptocurrencies. We demonstrate that the liquidity-adjusted model improves model fit for cryptocurrencies, with greater volatility sensitivity to past shocks and reduced volatility persistence of erratic past volatility. Our model is validated by the empirical evidence that the liquidity-adjusted mean-variance (LAMV) portfolios outperform the traditional mean-variance (TMV) portfolios.

q-fin.ST↗

arXiv2024

Learning to Generate Gradients for Test-Time Adaptation via Test-Time Training Layers

Test-time adaptation (TTA) aims to fine-tune a trained model online using unlabeled testing data to adapt to new environments or out-of-distribution data, demonstrating broad application potential in real-world scenarios. However, in this optimization process, unsupervised learning objectives like entropy minimization frequently encounter noisy learning signals. These signals produce unreliable gradients, which hinder the model ability to converge to an optimal solution quickly and introduce significant instability into the optimization process. In this paper, we seek to resolve these issues from the perspective of optimizer design. Unlike prior TTA using manually designed optimizers like SGD, we employ a learning-to-optimize approach to automatically learn an optimizer, called Meta Gradient Generator (MGG). Specifically, we aim for MGG to effectively utilize historical gradient information during the online optimization process to optimize the current model. To this end, in MGG, we design a lightweight and efficient sequence modeling layer -- gradient memory layer. It exploits a self-supervised reconstruction loss to compress historical gradient information into network parameters, thereby enabling better memorization ability over a long-term adaptation process. We only need a small number of unlabeled samples to pre-train MGG, and then the trained MGG can be deployed to process unseen samples. Promising results on ImageNet-C, R, Sketch, and A indicate that our method surpasses current state-of-the-art methods with fewer updates, less data, and significantly shorter adaptation iterations. Compared with a previous SOTA method SAR, we achieve 7.4% accuracy improvement and 4.2 times faster adaptation speed on ImageNet-C.

cs.LG↗

arXiv2024

Uniformly Optimal and Parameter-free First-order Methods for Convex and Function-constrained Optimization

This paper presents new first-order methods for achieving optimal oracle complexities in convex optimization with convex functional constraints. Oracle complexities are measured by the number of function and gradient evaluations. To achieve this, we enable first-order methods to utilize computational oracles for solving diagonal quadratic programs in subproblems. For problems where the optimal value $f^*$ is known, such as those in overparameterized models and feasibility problems, we propose an accelerated first-order method that incorporates a modified Polyak step size and Nesterov's momentum. Notably, our method does not require knowledge of smoothness levels, H\"{o}lder continuity parameter of the gradient, or additional line search, yet achieves the optimal oracle complexity bound of $\mathcal{O}(\varepsilon^{-2/(1+3\rho)})$ under H\"{o}lder smoothness conditions. When $f^*$ is unknown, we reformulate the problem as finding the root of the optimal value function and develop inexact fixed-point iteration and secant method to compute $f^*$. These root-finding subproblems are solved inexactly using first-order methods to a specified relative accuracy. We employ the accelerated prox-level (APL) method, which is proven to be uniformly optimal for convex optimization with simple constraints. Our analysis demonstrates that APL-based level-set methods also achieve the optimal oracle complexity of $\mathcal{O}(\varepsilon^{-2/(1+3\rho)})$ for convex function-constrained optimization, without requiring knowledge of any problem-specific structures. Through experiments on various tasks, we demonstrate the advantages of our methods over existing approaches in function-constrained optimization.

math.OC↗

arXiv2024

Spatio-temporal Causal Learning for Streamflow Forecasting

Streamflow plays an essential role in the sustainable planning and management of national water resources. Traditional hydrologic modeling approaches simulate streamflow by establishing connections across multiple physical processes, such as rainfall and runoff. These data, inherently connected both spatially and temporally, possess intrinsic causal relations that can be leveraged for robust and accurate forecasting. Recently, spatio-temporal graph neural networks (STGNNs) have been adopted, excelling in various domains, such as urban traffic management, weather forecasting, and pandemic control, and they also promise advances in streamflow management. However, learning causal relationships directly from vast observational data is theoretically and computationally challenging. In this study, we employ a river flow graph as prior knowledge to facilitate the learning of the causal structure and then use the learned causal graph to predict streamflow at targeted sites. The proposed model, Causal Streamflow Forecasting (CSF) is tested in a real-world study in the Brazos River basin in Texas. Our results demonstrate that our method outperforms regular spatio-temporal graph neural networks and achieves higher computational efficiency compared to traditional simulation methods. By effectively integrating river flow graphs with STGNNs, this research offers a novel approach to streamflow prediction, showcasing the potential of combining advanced neural network techniques with domain-specific knowledge for enhanced performance in hydrologic modeling.

cs.LG↗

arXiv2024

First Place Solution to the ECCV 2024 ROAD++ Challenge @ ROAD++ Spatiotemporal Agent Detection 2024

This report presents our team's solutions for the Track 1 of the 2024 ECCV ROAD++ Challenge. The task of Track 1 is spatiotemporal agent detection, which aims to construct an "agent tube" for road agents in consecutive video frames. Our solutions focus on the challenges in this task, including extreme-size objects, low-light scenarios, class imbalance, and fine-grained classification. Firstly, the extreme-size object detection heads are introduced to improve the detection performance of large and small objects. Secondly, we design a dual-stream detection model with a low-light enhancement stream to improve the performance of spatiotemporal agent detection in low-light scenes, and the feature fusion module to integrate features from different branches. Subsequently, we develop a multi-branch detection framework to mitigate the issues of class imbalance and fine-grained classification, and we design a pre-training and fine-tuning approach to optimize the above multi-branch framework. Besides, we employ some common data augmentation techniques, and improve the loss function and upsampling operation. We rank first in the test set of Track 1 for the ROAD++ Challenge 2024, and achieve 30.82% average video-mAP.

cs.CV↗

arXiv2024

Liquidity Jump, Liquidity Diffusion, and Crypto Wash Trading

We develop a new framework to detect wash trading in crypto assets through real-time liquidity fluctuation. We propose that short-term price jumps in crypto assets results from wash trading-induced liquidity fluctuation, and construct two complementary liquidity measures, liquidity jump (size of fluctuation) and liquidity diffusion (volatility of fluctuation), to capture the behavioral signature of wash trading. Using US stocks as a benchmark, we demonstrate that joint elevation in both liquidity metrics indicates wash trading in crypto assets. A simulated regulatory treatment that removes likely wash trades confirms this dynamic: it reduces liquidity diffusion significantly while leaving liquidity jump largely unaffected. These findings align with a theoretical model in which manipulative traders amplify both the level and variance of price pressure, whereas passive investors affect only the level. Our model offers practical tools for investors to assess market quality and for regulators to monitor manipulation risk on crypto exchanges without oversight.

q-fin.RM↗

arXiv2024

Accelerating Low-Rank Factorization-Based Semidefinite Programming Algorithms on GPU

In this paper, we address a long-standing challenge: how to achieve both efficiency and scalability in solving semidefinite programming problems. We propose breakthrough acceleration techniques for a wide range of low-rank factorization-based first-order methods using GPUs, making the computation much more efficient and scalable. To illustrate the idea and effectiveness of our approach, we use the low-rank factorization-based SDP solver, LoRADS, as an example, which involves both the classic Burer-Monterio method and a novel splitting scheme with a starting logarithmic rank. Our numerical results demonstrate that the accelerated GPU version of LoRADS, cuLoRADS, can solve huge-scale semidefinite programming problems with remarkable efficiency. By effectively leveraging GPU computational power, cuLoRADS exhibits outstanding performance. Specifically, it can solve a set of MaxCut problems with $10^7 \times 10^7$ matrix variables in 10 seconds to 1 minute each on an NVIDIA H100 GPU with 80GB memory, whereas previous solvers demonstrated the capability of handling problems of this scale, required at least dozens of hours per problem on CPUs. Additionally, cuLoRADS shows exceptional scalability by solving 1) a MaxCut problem with a $170 \text{ million} \times 170 \text{ million}$ matrix variable and 2) a Matrix Completion problem with a 20 million $\times$ 20 million matrix variable and approximately 200 million constraints, both in a matter of minutes.

math.OC↗

arXiv2024

A Single-Loop Robust Policy Gradient Method for Robust Markov Decision Processes

Robust Markov Decision Processes (RMDPs) have recently been recognized as a valuable and promising approach to discovering a policy with creditable performance, particularly in the presence of a dynamic environment and estimation errors in the transition matrix due to limited data. Despite extensive exploration of dynamic programming algorithms for solving RMDPs, there has been a notable upswing in interest in developing efficient algorithms using the policy gradient method. In this paper, we propose the first single-loop robust policy gradient (SRPG) method with the global optimality guarantee for solving RMDPs through its minimax formulation. Moreover, we complement the convergence analysis of the nonconvex-nonconcave min-max optimization problem with the objective function's gradient dominance property, which is not explored in the prior literature. Numerical experiments validate the efficacy of SRPG, demonstrating its faster and more robust convergence behavior compared to its nested-loop counterpart.

math.OC↗