arXiv subjects

Ruixuan Liu

Publications and source records attributed to Ruixuan Liu.

At least 55 records · Page 3Linked to original sources

arXiv2024

GUARD: A Safe Reinforcement Learning Benchmark

Due to the trial-and-error nature, it is typically challenging to apply RL algorithms to safety-critical real-world applications, such as autonomous driving, human-robot interaction, robot manipulation, etc, where such errors are not tolerable. Recently, safe RL (i.e. constrained RL) has emerged rapidly in the literature, in which the agents explore the environment while satisfying constraints. Due to the diversity of algorithms and tasks, it remains difficult to compare existing safe RL algorithms. To fill that gap, we introduce GUARD, a Generalized Unified SAfe Reinforcement Learning Development Benchmark. GUARD has several advantages compared to existing benchmarks. First, GUARD is a generalized benchmark with a wide variety of RL agents, tasks, and safety constraint specifications. Second, GUARD comprehensively covers state-of-the-art safe RL algorithms with self-contained implementations. Third, GUARD is highly customizable in tasks and algorithms. We present a comparison of state-of-the-art safe RL algorithms in various task settings using GUARD and establish baselines that future work can build on.

cs.LG↗

arXiv2024

PreCurious: How Innocent Pre-Trained Language Models Turn into Privacy Traps

The pre-training and fine-tuning paradigm has demonstrated its effectiveness and has become the standard approach for tailoring language models to various tasks. Currently, community-based platforms offer easy access to various pre-trained models, as anyone can publish without strict validation processes. However, a released pre-trained model can be a privacy trap for fine-tuning datasets if it is carefully designed. In this work, we propose PreCurious framework to reveal the new attack surface where the attacker releases the pre-trained model and gets a black-box access to the final fine-tuned model. PreCurious aims to escalate the general privacy risk of both membership inference and data extraction on the fine-tuning dataset. The key intuition behind PreCurious is to manipulate the memorization stage of the pre-trained model and guide fine-tuning with a seemingly legitimate configuration. While empirical and theoretical evidence suggests that parameter-efficient and differentially private fine-tuning techniques can defend against privacy attacks on a fine-tuned model, PreCurious demonstrates the possibility of breaking up this invulnerability in a stealthy manner compared to fine-tuning on a benign pre-trained model. While DP provides some mitigation for membership inference attack, by further leveraging a sanitized dataset, PreCurious demonstrates potential vulnerabilities for targeted data extraction even under differentially private tuning with a strict privacy budget e.g. $ε=0.05$. Thus, PreCurious raises warnings for users on the potential risks of downloading pre-trained models from unknown sources, relying solely on tutorials or common-sense defenses, and releasing sanitized datasets even after perfect scrubbing.

cs.CR↗

arXiv2024

Automating Robot Failure Recovery Using Vision-Language Models With Optimized Prompts

Current robot autonomy struggles to operate beyond the assumed Operational Design Domain (ODD), the specific set of conditions and environments in which the system is designed to function, while the real-world is rife with uncertainties that may lead to failures. Automating recovery remains a significant challenge. Traditional methods often rely on human intervention to manually address failures or require exhaustive enumeration of failure cases and the design of specific recovery policies for each scenario, both of which are labor-intensive. Foundational Vision-Language Models (VLMs), which demonstrate remarkable common-sense generalization and reasoning capabilities, have broader, potentially unbounded ODDs. However, limitations in spatial reasoning continue to be a common challenge for many VLMs when applied to robot control and motion-level error recovery. In this paper, we investigate how optimizing visual and text prompts can enhance the spatial reasoning of VLMs, enabling them to function effectively as black-box controllers for both motion-level position correction and task-level recovery from unknown failures. Specifically, the optimizations include identifying key visual elements in visual prompts, highlighting these elements in text prompts for querying, and decomposing the reasoning process for failure detection and control generation. In experiments, prompt optimizations significantly outperform pre-trained Vision-Language-Action Models in correcting motion-level position errors and improve accuracy by 65.78% compared to VLMs with unoptimized prompts. Additionally, for task-level failures, optimized prompts enhanced the success rate by 5.8%, 5.8%, and 7.5% in VLMs' abilities to detect failures, analyze issues, and generate recovery plans, respectively, across a wide range of unknown errors in Lego assembly.

cs.RO↗

arXiv2024

Chern insulator phase realized in dual-gate-tuned MnBi2Te4 thin films grown by molecular beam epitaxy

The intrinsic magnetic order, large topological-magnetic gap and rich topological phases make MnBi2Te4 a wonderful platform to study exotic topological quantum states such as axion insulator and Chern insulator. To realize and manipulate these topological phases in a MnBi2Te4 thin film, precise manipulation of the electric field across the film is essential, which requires a dual-gate structure. In this work, we achieve dual-gate tuning of MnBi2Te4 thin films grown with molecular beam epitaxy on SrTiO3(111) substrates by applying the substrate and an AlOx layer as the gate dielectrics of bottom and top gates, respectively. Under magnetic field of 9T and temperature of 20 mK, the Hall and longitudinal resistivities of the films show inversed gate-voltage dependence, for both top- and bottom-gates, signifying the existence of the dissipationless edge state contributed by Chern insulator phase in the ferromagnetic configuration. The maximum of the Hall resistivity only reaches 0.8 h/e2, even with dual-gate tuning, probably due to the high density of bulk carriers introduced by secondary phases. In the antiferromagnetic state under zero magnetic field, the films show normal insulator behavior. The dual-gated MnBi2Te4 thin films lay the foundation for developing devices based on electrically tunable topological quantum states.

cond-mat.mtrl-sci↗

arXiv2024

DPDR: Gradient Decomposition and Reconstruction for Differentially Private Deep Learning

Differentially Private Stochastic Gradients Descent (DP-SGD) is a prominent paradigm for preserving privacy in deep learning. It ensures privacy by perturbing gradients with random noise calibrated to their entire norm at each training step. However, this perturbation suffers from a sub-optimal performance: it repeatedly wastes privacy budget on the general converging direction shared among gradients from different batches, which we refer as common knowledge, yet yields little information gain. Motivated by this, we propose a differentially private training framework with early gradient decomposition and reconstruction (DPDR), which enables more efficient use of the privacy budget. In essence, it boosts model utility by focusing on incremental information protection and recycling the privatized common knowledge learned from previous gradients at early training steps. Concretely, DPDR incorporates three steps. First, it disentangles common knowledge and incremental information in current gradients by decomposing them based on previous noisy gradients. Second, most privacy budget is spent on protecting incremental information for higher information gain. Third, the model is updated with the gradient reconstructed from recycled common knowledge and noisy incremental information. Theoretical analysis and extensive experiments show that DPDR outperforms state-of-the-art baselines on both convergence rate and accuracy.

cs.CR↗

arXiv2024

Clip Body and Tail Separately: High Probability Guarantees for DPSGD with Heavy Tails

Differentially Private Stochastic Gradient Descent (DPSGD) is widely utilized to preserve training data privacy in deep learning, which first clips the gradients to a predefined norm and then injects calibrated noise into the training procedure. Existing DPSGD works typically assume the gradients follow sub-Gaussian distributions and design various clipping mechanisms to optimize training performance. However, recent studies have shown that the gradients in deep learning exhibit a heavy-tail phenomenon, that is, the tails of the gradient have infinite variance, which may lead to excessive clipping loss to the gradients with existing DPSGD mechanisms. To address this problem, we propose a novel approach, Discriminative Clipping~(DC)-DPSGD, with two key designs. First, we introduce a subspace identification technique to distinguish between body and tail gradients. Second, we present a discriminative clipping mechanism that applies different clipping thresholds for body and tail gradients to reduce the clipping loss. Under the non-convex condition, \ourtech{} reduces the empirical gradient norm from {${\mathbb{O}\left(\log^{\max(0,θ-1)}(T/δ)\log^{2θ}(\sqrt{T})\right)}$} to {${\mathbb{O}\left(\log(\sqrt{T})\right)}$} with heavy-tailed index $θ\geq 1/2$, iterations $T$, and arbitrary probability $δ$. Extensive experiments on four real-world datasets demonstrate that our approach outperforms three baselines by up to 9.72\% in terms of accuracy.

cs.LG↗

arXiv2024

Decomposition-based Hierarchical Task Allocation and Planning for Multi-Robots under Hierarchical Temporal Logic Specifications

Past research into robotic planning with temporal logic specifications, notably Linear Temporal Logic (LTL), was largely based on a single formula for individual or groups of robots. But with increasing task complexity, LTL formulas unavoidably grow lengthy, complicating interpretation and specification generation, and straining the computational capacities of the planners. A recent development has been the hierarchical representation of LTL~\cite{luo2024simultaneous} that contains multiple temporal logic specifications, providing a more interpretable framework. However, the proposed planning algorithm assumes the independence of robots within each specification, limiting their application to multi-robot coordination with complex temporal constraints. In this work, we formulated a decomposition-based hierarchical framework. At the high level, each specification is first decomposed into a set of atomic sub-tasks. We further infer the temporal relations among the sub-tasks of different specifications to construct a task network. Subsequently, a Mixed Integer Linear Program is used to assign sub-tasks to various robots. At the lower level, domain-specific controllers are employed to execute sub-tasks. Our approach was experimentally applied to domains of navigation and manipulation. The simulation demonstrated that our approach can find better solutions using less runtimes.

cs.RO↗

arXiv2024

A Lightweight and Transferable Design for Robust LEGO Manipulation

Lego is a well-known platform for prototyping pixelized objects. However, robotic Lego prototyping (i.e., manipulating Lego bricks) is challenging due to the tight connections and accuracy requirements. This paper investigates safe and efficient robotic Lego manipulation. In particular, this paper reduces the complexity of the manipulation by hardware-software co-design. An end-of-arm tool (EOAT) is designed, which reduces the problem dimension and allows large industrial robots to manipulate small Lego bricks. In addition, this paper uses evolution strategy to optimize the robot motion for Lego manipulation. Experiments demonstrate that the EOAT can reliably manipulate Lego bricks and the learning framework can effectively and safely improve the manipulation performance to a 100% success rate. The co-design is deployed to multiple robots (i.e., FANUC LR-mate 200id/7L and Yaskawa GP4) to demonstrate its generalizability and transferability. In the end, we show that the proposed solution enables sustainable robotic Lego prototyping, in which the robot can repeatedly assemble and disassemble different prototypes.

cs.RO↗

arXiv2024

KoReA-SFL: Knowledge Replay-based Split Federated Learning Against Catastrophic Forgetting

Although Split Federated Learning (SFL) is good at enabling knowledge sharing among resource-constrained clients, it suffers from the problem of low training accuracy due to the neglect of data heterogeneity and catastrophic forgetting. To address this issue, we propose a novel SFL approach named KoReA-SFL, which adopts a multi-model aggregation mechanism to alleviate gradient divergence caused by heterogeneous data and a knowledge replay strategy to deal with catastrophic forgetting. Specifically, in KoReA-SFL cloud servers (i.e., fed server and main server) maintain multiple branch model portions rather than a global portion for local training and an aggregated master-model portion for knowledge sharing among branch portions. To avoid catastrophic forgetting, the main server of KoReA-SFL selects multiple assistant devices for knowledge replay according to the training data distribution of each server-side branch-model portion. Experimental results obtained from non-IID and IID scenarios demonstrate that KoReA-SFL significantly outperforms conventional SFL methods (by up to 23.25\% test accuracy improvement).

cs.LG↗

arXiv2024

Real-time Safety Index Adaptation for Parameter-varying Systems via Determinant Gradient Ascend

Safety Index Synthesis (SIS) is critical for deriving safe control laws. Recent works propose to synthesize a safety index (SI) via nonlinear programming and derive a safe control law such that the system 1) achieves forward invariant (FI) with some safe set and 2) guarantees finite time convergence (FTC) to that safe set. However, real-world system dynamics can vary during run-time, making the control law infeasible and invalidating the initial SI. Since the full SIS nonlinear programming is computationally expensive, it is infeasible to re-synthesize the SI each time the dynamics are perturbed. To address that, this paper proposes an efficient approach to adapting the SI to varying system dynamics and maintaining the feasibility of the safe control law. The proposed method leverages determinant gradient ascend and derives a closed-form update to safety index parameters, enabling real-time adaptation performance. A numerical study validates the effectiveness of our approach.

eess.SY↗

arXiv2024

Correlation between magnetic domain structures and quantum anomalous Hall effect in epitaxial MnBi2Te4 thin films

We use magnetic force microscopy (MFM) to study spatial uniformity of magnetization of epitaxially grown MnBi2Te4 thin films. Compared to films which exhibit no quantum anomalous Hall effect (QAH), films with QAH are observed to have more spatial uniformity of magnetization with larger domain size. The domain evolution upon magnetic field sweeping indicates that the magnetic domains or the spatial nonuniformity of magnetization originates from the strong pinning of the inherent sample inhomogeneity. A direct correlation between the Hall resistivity and the domain size has been established by analyzing a series of thin films with and without QAH. Our observation shows that one has to suppress the spatial nonuniformity of magnetization to allow the Hall resistivity to be quantized. The fact that a sizable longitudinal resistivity remains even for the QAH sample suggests a quantized Hall insulator scenario. Our work provides important insights to the understanding of the quantization mechanism and the dissipation of the QAH state in MnBi2Te4 system.

cond-mat.mes-hall↗

arXiv2024

Reentrant quantum anomalous Hall effect in molecular beam epitaxy-grown MnBi2Te4 thin films

In this study, we investigate intrinsic magnetic topological insulator MnBi2Te4 thin films grown by molecular beam epitaxy. We observe a reentrant quantum anomalous Hall effect when the Fermi energy enters the valance band and magnetic field equals zero, indicating the emergence of the Chern Anderson insulator state. The discovery opens a new avenue for realizing the QAH effect and underscores the fundamental role of both Berry curvature and Anderson localization.

cond-mat.mes-hall↗

arXiv2023

AdapterFL: Adaptive Heterogeneous Federated Learning for Resource-constrained Mobile Computing Systems

Federated Learning (FL) enables collaborative learning of large-scale distributed clients without data sharing. However, due to the disparity of computing resources among massive mobile computing devices, the performance of traditional homogeneous model-based Federated Learning (FL) is seriously limited. On the one hand, to achieve model training in all the diverse clients, mobile computing systems can only use small low-performance models for collaborative learning. On the other hand, devices with high computing resources cannot train a high-performance large model with their insufficient raw data. To address the resource-constrained problem in mobile computing systems, we present a novel heterogeneous FL approach named AdapterFL, which uses a model reassemble strategy to facilitate collaborative training of massive heterogeneous mobile devices adaptively. Specifically, we select multiple candidate heterogeneous models based on the computing performance of massive mobile devices and then divide each heterogeneous model into two partitions. By reassembling the partitions, we can generate models with varied sizes that are combined by the partial parameters of the large model with the partial parameters of the small model. Using these reassembled models for FL training, we can train the partial parameters of the large model using low-performance devices. In this way, we can alleviate performance degradation in large models due to resource constraints. The experimental results show that AdapterFL can achieve up to 12\% accuracy improvement compared to the state-of-the-art heterogeneous federated learning methods in resource-constrained scenarios.

cs.LG↗

arXiv2023

Zero redundancy distributed learning with differential privacy

Deep learning using large models have achieved great success in a wide range of domains. However, training these models on billions of parameters is very challenging in terms of the training speed, memory cost, and communication efficiency, especially under the privacy-preserving regime with differential privacy (DP). On the one hand, DP optimization has comparable efficiency to the standard non-private optimization on a single GPU, but on multiple GPUs, existing DP distributed learning (such as pipeline parallel) has suffered from significantly worse efficiency. On the other hand, the Zero Redundancy Optimizer (ZeRO) is a state-of-the-art solution to the standard distributed learning, exhibiting excellent training efficiency on large models, but to work compatibly with DP is technically complicated. In this work, we develop a new systematic solution, DP-ZeRO, (I) to scale up the trainable DP model size, e.g. to GPT-100B, (II) to obtain the same computation and communication efficiency as the standard ZeRO, and (III) to enable mixed-precision DP training. Our DP-ZeRO, like the standard ZeRO, has the potential to train models with arbitrary size and is evaluated on the world's largest DP models in terms of the number of trainable parameters.

cs.LG↗

arXiv2023

On the accuracy and efficiency of group-wise clipping in differentially private optimization

Recent advances have substantially improved the accuracy, memory cost, and training speed of differentially private (DP) deep learning, especially on large vision and language models with millions to billions of parameters. In this work, we thoroughly study the per-sample gradient clipping style, a key component in DP optimization. We show that different clipping styles have the same time complexity but instantiate an accuracy-memory trade-off: while the all-layer clipping (of coarse granularity) is the most prevalent and usually gives the best accuracy, it incurs heavier memory cost compared to other group-wise clipping, such as the layer-wise clipping (of finer granularity). We formalize this trade-off through our convergence theory and complexity analysis. Importantly, we demonstrate that the accuracy gap between group-wise clipping and all-layer clipping becomes smaller for larger models, while the memory advantage of the group-wise clipping remains. Consequently, the group-wise clipping allows DP optimization of large models to achieve high accuracy and low peak memory simultaneously.

cs.LG↗

arXiv2023

Coupling public and private gradient provably helps optimization

The success of large neural networks is crucially determined by the availability of data. It has been observed that training only on a small amount of public data, or privately on the abundant private data can lead to undesirable degradation of accuracy. In this work, we leverage both private and public data to improve the optimization, by coupling their gradients via a weighted linear combination. We formulate an optimal solution for the optimal weight in the convex setting to indicate that the weighting coefficient should be hyperparameter-dependent. Then, we prove the acceleration in the convergence of non-convex loss and the effects of hyper-parameters such as privacy budget, number of iterations, batch size, and model size on the choice of the weighting coefficient. We support our analysis with empirical experiments across language and vision benchmarks, and provide a guideline for choosing the optimal weight of the gradient coupling.

cs.LG↗

arXiv2023

Simulation-aided Learning from Demonstration for Robotic LEGO Construction

Recent advancements in manufacturing have a growing demand for fast, automatic prototyping (i.e. assembly and disassembly) capabilities to meet users' needs. This paper studies automatic rapid LEGO prototyping, which is devoted to constructing target LEGO objects that satisfy individual customization needs and allow users to freely construct their novel designs. A construction plan is needed in order to automatically construct the user-specified LEGO design. However, a freely designed LEGO object might not have an existing construction plan, and generating such a LEGO construction plan requires a non-trivial effort since it requires accounting for numerous constraints (e.g. object shape, colors, stability, etc.). In addition, programming the prototyping skill for the robot requires the users to have expert programming skills, which makes the task beyond the reach of the general public. To address the challenges, this paper presents a simulation-aided learning from demonstration (SaLfD) framework for easily deploying LEGO prototyping capability to robots. In particular, the user demonstrates constructing the customized novel LEGO object. The robot extracts the task information by observing the human operation and generates the construction plan. A simulation is developed to verify the correctness of the learned construction plan and the resulting LEGO prototype. The proposed system is deployed to a FANUC LR-mate 200id/7L robot. Experiments demonstrate that the proposed SaLfD framework can effectively correct and learn the prototyping (i.e. assembly and disassembly) tasks from human demonstrations. And the learned prototyping tasks are realized by the FANUC robot.

cs.RO↗

arXiv2023

SoccerNet 2023 Challenges Results

The SoccerNet 2023 challenges were the third annual video understanding challenges organized by the SoccerNet team. For this third edition, the challenges were composed of seven vision-based tasks split into three main themes. The first theme, broadcast video understanding, is composed of three high-level tasks related to describing events occurring in the video broadcasts: (1) action spotting, focusing on retrieving all timestamps related to global actions in soccer, (2) ball action spotting, focusing on retrieving all timestamps related to the soccer ball change of state, and (3) dense video captioning, focusing on describing the broadcast with natural language and anchored timestamps. The second theme, field understanding, relates to the single task of (4) camera calibration, focusing on retrieving the intrinsic and extrinsic camera parameters from images. The third and last theme, player understanding, is composed of three low-level tasks related to extracting information about the players: (5) re-identification, focusing on retrieving the same players across multiple views, (6) multiple object tracking, focusing on tracking players and the ball through unedited video streams, and (7) jersey number recognition, focusing on recognizing the jersey number of players from tracklets. Compared to the previous editions of the SoccerNet challenges, tasks (2-3-7) are novel, including new annotations and data, task (4) was enhanced with more data and annotations, and task (6) now focuses on end-to-end approaches. More information on the tasks, challenges, and leaderboards are available on https://www.soccer-net.org. Baselines and development kits can be found on https://github.com/SoccerNet.

cs.CV↗