arXiv subjects

Yiwen Lu

Publications and source records attributed to Yiwen Lu.

32 records · Page 2Linked to original sources

arXiv2024

From Basic to Extra Features: Hypergraph Transformer Pretrain-then-Finetuning for Balanced Clinical Predictions on EHR

Electronic Health Records (EHRs) contain rich patient information and are crucial for clinical research and practice. In recent years, deep learning models have been applied to EHRs, but they often rely on massive features, which may not be readily available for all patients. We propose HTP-Star, which leverages hypergraph structures with a pretrain-then-finetune framework for modeling EHR data, enabling seamless integration of additional features. Additionally, we design two techniques, namely (1) Smoothness-inducing Regularization and (2) Group-balanced Reweighting, to enhance the model's robustness during fine-tuning. Through experiments conducted on two real EHR datasets, we demonstrate that HTP-Star consistently outperforms various baselines while striking a balance between patients with basic and extra features.

cs.LG↗

arXiv2024

MPC-Inspired Reinforcement Learning for Verifiable Model-Free Control

In this paper, we introduce a new class of parameterized controllers, drawing inspiration from Model Predictive Control (MPC). The controller resembles a Quadratic Programming (QP) solver of a linear MPC problem, with the parameters of the controller being trained via Deep Reinforcement Learning (DRL) rather than derived from system models. This approach addresses the limitations of common controllers with Multi-Layer Perceptron (MLP) or other general neural network architecture used in DRL, in terms of verifiability and performance guarantees, and the learned controllers possess verifiable properties like persistent feasibility and asymptotic stability akin to MPC. On the other hand, numerical examples illustrate that the proposed controller empirically matches MPC and MLP controllers in terms of control performance and has superior robustness against modeling uncertainty and noises. Furthermore, the proposed controller is significantly more computationally efficient compared to MPC and requires fewer parameters to learn than MLP controllers. Real-world experiments on vehicle drift maneuvering task demonstrate the potential of these controllers for robotics and other demanding control tasks.

eess.SY↗

arXiv2024

Generalized Activation via Multivariate Projection

Activation functions are essential to introduce nonlinearity into neural networks, with the Rectified Linear Unit (ReLU) often favored for its simplicity and effectiveness. Motivated by the structural similarity between a shallow Feedforward Neural Network (FNN) and a single iteration of the Projected Gradient Descent (PGD) algorithm, a standard approach for solving constrained optimization problems, we consider ReLU as a projection from R onto the nonnegative half-line R+. Building on this interpretation, we extend ReLU by substituting it with a generalized projection operator onto a convex cone, such as the Second-Order Cone (SOC) projection, thereby naturally extending it to a Multivariate Projection Unit (MPU), an activation function with multiple inputs and multiple outputs. We further provide mathematical proof establishing that FNNs activated by SOC projections outperform those utilizing ReLU in terms of expressive power. Experimental evaluations on widely-adopted architectures further corroborate MPU's effectiveness against a broader range of existing activation functions.

cs.LG↗

arXiv2024

CoMoSVC: Consistency Model-based Singing Voice Conversion

The diffusion-based Singing Voice Conversion (SVC) methods have achieved remarkable performances, producing natural audios with high similarity to the target timbre. However, the iterative sampling process results in slow inference speed, and acceleration thus becomes crucial. In this paper, we propose CoMoSVC, a consistency model-based SVC method, which aims to achieve both high-quality generation and high-speed sampling. A diffusion-based teacher model is first specially designed for SVC, and a student model is further distilled under self-consistency properties to achieve one-step sampling. Experiments on a single NVIDIA GTX4090 GPU reveal that although CoMoSVC has a significantly faster inference speed than the state-of-the-art (SOTA) diffusion-based SVC system, it still achieves comparable or superior conversion performance based on both subjective and objective metrics. Audio samples and codes are available at https://comosvc.github.io/.

eess.AS↗

arXiv2023

Consecutive Inertia Drift of Autonomous RC Car via Primitive-based Planning and Data-driven Control

Inertia drift is an aggressive transitional driving maneuver, which is challenging due to the high nonlinearity of the system and the stringent requirement on control and planning performance. This paper presents a solution for the consecutive inertia drift of an autonomous RC car based on primitive-based planning and data-driven control. The planner generates complex paths via the concatenation of path segments called primitives, and the controller eases the burden on feedback by interpolating between multiple real trajectories with different initial conditions into one near-feasible reference trajectory. The proposed strategy is capable of drifting through various paths containing consecutive turns, which is validated in both simulation and reality.

cs.RO↗

arXiv2023

Safe and Efficient Switching Controller Design for Partially Observed Linear-Gaussian Systems

Switching control strategies that unite a potentially high-performance but uncertified controller and a stabilizing albeit conservative controller are shown to be able to balance safety with efficiency, but have been less studied under partial observation of state. To address this gap, we propose a switching control strategy for partially observed linear-Gaussian systems with provable performance guarantees. We show that the proposed switching strategy is both safe and efficient, in the sense that: (1) the linear-quadratic cost of the system is always bounded even if the original uncertified controller is destabilizing; (2) in the case when the uncertified controller is stabilizing, the performance loss induced by the conservativeness of switching converges super-exponentially to zero. The effectiveness of the switching strategy is also demonstrated via numerical simulation on the Tennessee Eastman Process.

eess.SY↗

arXiv2023

Two-timescale Mechanism-and-Data-Driven Control for Aggressive Driving of Autonomous Cars

The control for aggressive driving of autonomous cars is challenging due to the presence of significant tyre slip. Data-driven and mechanism-based methods for the modeling and control of autonomous cars under aggressive driving conditions are limited in data efficiency and adaptability respectively. This paper is an attempt toward the fusion of the two classes of methods. By means of a modular design that is consisted of mechanism-based and data-driven components, and aware of the two-timescale phenomenon in the car model, our approach effectively improves over previous methods in terms of data efficiency, ability of transfer and final performance. The hybrid mechanism-and-data-driven approach is verified on TORCS (The Open Racing Car Simulator). Experiment results demonstrate the benefit of our approach over purely mechanism-based and purely data-driven methods.

cs.RO↗

arXiv2022

Distribution of the k-regular partition function modulo composite integers M

Let $b_k(n)$ denote the $k-$regular partitons of a natural number $n$. In this paper, we study the behavior of $b_k(n)$ modulo composite integers $M$ which are coprime to $6$. Specially, we prove that for arbitrary $k-$regular partiton function $b_k(n)$ and integer $M$ coprime to $6$, there are infinitely many Ramanujan-type congruences of $b_k(n)$ modulo $M$.

math.NT↗

arXiv2022

An improvement on the parity of Schur's partition function

We improve S.-C. Chen's result on the parity of Schur's partition function. Let $A(n)$ be the number of Schur's partitions of $n$, i.e., the number of partitions of $n$ into distinct parts congruent to $1, 2 \mod{3}$. S.-C. Chen \cite{MR3959837} shows $\small \frac{x}{(\log{x})^{\frac{47}{48}}} \ll \sharp \{0\le n\le x:A(2n+1)\; \text{is odd}\}\ll \frac{x}{(\log{x})^{\frac{1}{2}}}$. In this paper, we improve Chen's result to $\frac{x}{(\log{x})^{\frac{11}{12}}} \ll \sharp \{0\le n\le x:A(2n+1)\; \text{is odd}\}\ll \frac{x}{(\log{x})^{\frac{1}{2}}}.$

math.NT↗

arXiv2022

Safe and Efficient Switching Mechanism Design for Uncertified Linear Controller

Sustained research efforts have been devoted to learning optimal controllers for linear stochastic dynamical systems with unknown parameters, but due to the corruption of noise, learned controllers are usually uncertified in the sense that they may destabilize the system. To address this potential instability, we propose a "plug-and-play" modification to the uncertified controller which falls back to a known stabilizing controller when the norm of the difference between the uncertified and the fall-back control input exceeds a certain threshold. We show that the switching strategy is both safe and efficient, in the sense that: 1) the linear-quadratic cost of the system is always bounded even if original uncertified controller is destabilizing; 2) in case the uncertified controller is stabilizing, the performance loss caused by switching converges super-exponentially to $0$ for Gaussian noise, while the converging polynomially for general heavy-tailed noise. Finally, we demonstrate the effectiveness of the proposed switching strategy via numerical simulation on the Tennessee Eastman Process.

eess.SY↗

arXiv2022

Ensuring the Safety of Uncertified Linear State-Feedback Controllers via Switching

Sustained research efforts have been devoted to learning optimal controllers for linear stochastic dynamical systems with unknown parameters, but due to the corruption of noise, learned controllers are usually uncertified in the sense that they may destabilize the system. To address this potential instability, we propose a "plug-and-play" modification to the uncertified controller which falls back to a known stabilizing controller when the norm of the state exceeds a certain threshold. We show that the switching strategy enhances the safety of the uncertified controller by making the linear-quadratic cost bounded even if the underlying linear feedback gain is destabilizing. We also prove the near-optimality of the proposed strategy by quantifying the maximum performance loss caused by switching as asymptotically negligible. Finally, we demonstrate the effectiveness of the proposed switching strategy using simulation on an industrial process example.

eess.SY↗

arXiv2021

A Hierarchical Control Framework for Drift Maneuvering of Autonomous Vehicles

Drift control is significant to the safety of autonomous vehicles when there is a sudden loss of traction due to external conditions such as rain or snow. It is a challenging control problem due to the presence of significant sideslip and nearly full saturation of the tires. In this paper, we focus on the control of drift maneuvers following circular paths with either fixed or moving centers, subject to change in the tire-ground interaction, which are common training tasks for drift enthusiasts and can therefore be used as benchmarks of the performance of drift control. In order to achieve the above tasks, we propose a novel hierarchical control architecture which decouples the curvature and center control of the trajectory. In particular, an outer loop stabilizes the center by tuning the target curvature, and an inner loop tracks the curvature using a feedforward/feedback controller enhanced by an $\mathcal{L}_1$ adaptive component. The hierarchical architecture is flexible because the inner loop is task-agnostic and adaptive to changes in tire-road interaction, which allows the outer loop to be designed independent of low-level dynamics, opening up the possibility of incorporating sophisticated planning algorithms. We implement our control strategy on a simulation platform as well as on a 1/10 scale Radio-Control~(RC) car, and both the simulation and experiment results illustrate the effectiveness of our strategy in achieving the above described set of drift maneuvering tasks.

cs.RO↗

arXiv2021

Safe Linear-Quadratic Dual Control with Almost Sure Performance Guarantee

This paper considers the linear-quadratic dual control problem where the system parameters need to be identified and the control objective needs to be optimized in the meantime. Contrary to existing works on data-driven linear-quadratic regulation, which typically provide error or regret bounds within a certain probability, we propose an online algorithm that guarantees the asymptotic optimality of the controller in the almost sure sense. Our dual control strategy consists of two parts: a switched controller with time-decaying exploration noise and Markov parameter inference based on the cross-correlation between the exploration noise and system output. Central to the almost sure performance guarantee is a safe switched control strategy that falls back to a known conservative but stable controller when the actual state deviates significantly from the target state. We prove that this switching strategy rules out any potential destabilizing controllers from being applied, while the performance gap between our switching strategy and the optimal linear state feedback is exponentially small. Under our dual control scheme, the parameter inference error scales as $O(T^{-1/4+ε})$, while the suboptimality gap of control performance scales as $O(T^{-1/2+ε})$, where $T$ is the number of time steps, and $ε$ is an arbitrarily small positive number. Simulation results on an industrial process example are provided to illustrate the effectiveness of our proposed strategy.

eess.SY↗

arXiv2021

Modeling the Interaction between Agents in Cooperative Multi-Agent Reinforcement Learning

Value-based methods of multi-agent reinforcement learning (MARL), especially the value decomposition methods, have been demonstrated on a range of challenging cooperative tasks. However, current methods pay little attention to the interaction between agents, which is essential to teamwork in games or real life. This limits the efficiency of value-based MARL algorithms in the two aspects: collaborative exploration and value function estimation. In this paper, we propose a novel cooperative MARL algorithm named as interactive actor-critic~(IAC), which models the interaction of agents from the perspectives of policy and value function. On the policy side, a multi-agent joint stochastic policy is introduced by adopting a collaborative exploration module, which is trained by maximizing the entropy-regularized expected return. On the value side, we use the shared attention mechanism to estimate the value function of each agent, which takes the impact of the teammates into consideration. At the implementation level, we extend the value decomposition methods to continuous control tasks and evaluate IAC on benchmark tasks including classic control and multi-agent particle environments. Experimental results indicate that our method outperforms the state-of-the-art approaches and achieves better performance in terms of cooperation.

cs.LG↗