arXiv subjects

Rong Chen

Publications and source records attributed to Rong Chen.

At least 37 records · Page 2Linked to original sources

arXiv2026

A counterexample to Hickingbotham's conjecture about $k$-ghost-edges

Fix $k\in \mathbb{N}$ and let $G$ be a connected graph with $tw(G)\leq k$. We say that $xy\in E(G^c)$ is a {\em $k$-ghost-edge} of $G$ if for every tree decomposition $(T,\cB)$ of $G$ with width at most $k$, the set $\{x,y\}$ is contained in a bag of $(T,\cB)$. Although a $k$-ghost-edge of $G$ is not an edge of $G$, but it behaves like real edges with respect to tree decomposition of $G$ with width at most $k$. For any graph $G$ with treewidth $k$ and $xy\in E(G^c)$, when there are at least $k+1$ internally vertex disjoint $(x,y)$-paths, Hickingbotham proved that $xy$ is a $k$-ghost-edge of $G$; while when there are at most $k$ internally vertex disjoint $(x,y)$-paths, he conjectured that it is not a $k$-ghost-edge of $G$. In this paper, we prove that this conjecture is wrong.

math.CO↗

arXiv2026

Towards Fully-fledged GPU Multitasking via Proactive Memory Scheduling

The limited HBM capacity has become the primary bottleneck for hosting an increasing number of larger-scale GPU tasks. While demand paging extends capacity via host DRAM, it incurs up to 78x slowdown due to the massive working sets and poor locality of GPU workloads. We observe, however, that GPU memory access patterns are inherently predictable via kernel launch arguments and their asynchronous execution nature. Leveraging this, we propose MSched, an OS-level scheduler that extends GPU context switching to include proactive working set preparation, thereby coalescing fragmented, eventual, and expensive page faults into a single efficient migration. MSched employs a template-based approach to predict working sets with near-perfect accuracy and proposes a co-design between task scheduler and memory manager to enforce a globally optimal page placement policy. Evaluation demonstrates that MSched outperforms demand paging by up to 11.05x for scientific and deep learning workloads, and 57.88x for LLM under memory oversubscription.

cs.OS↗

arXiv2025

Fast LLM Post-training via Decoupled and Fastest-of-N Speculation

Rollout dominates the training time in large language model (LLM) post-training, where the trained model is used to generate tokens given a batch of prompts. This work, SpecActor, achieves fast rollout with speculative decoding that deploys a fast draft path to accelerate the unparallelizable generation, while the correctness is guaranteed by fast parallel verification of the outputs with the original model. SpecActor addresses two foundational challenges that hinder speculation efficiency: (1) a Decoupled speculation method that overcomes the computation inefficiency issue when executing speculative decoding with relative large per-worker batch size -- a common configuration in training but unfriendly to speculation, and (2) a Fastest-of-N speculation method that selects and combines different draft methods according to the rollout progress to approximate the optimal draft method even when the best one is unknown a priori. Extensive evaluations on production traces show that SpecActor accelerates mean rollout speed by 2.0--2.4x, with up to 2.7x speedup, over common post-training baselines. The results are consistent across both dense and MoE models and across different RL algorithms. Notably, SpecActor is 1.1--2.6x faster compared to vanilla speculative rollout in different traces. The accelerated rollout achieves 1.4--2.3x faster end-to-end training time.

cs.DC↗

arXiv2025

Large longitudinal and anomalous transverse Magneto-thermoelectric effect in kagome antiferromagnet FeGe

Topological Kagome magnets, characterized by nontrivial electronic band structures featuring flat band, Dirac cone and van Hove singularities, provide a new avenue for the realization of thermoelectric devices. Unlike the conventional longitudinal Seebeck effect, transverse thermoelectric (TE) effects like the Nernst effect have attracted growing interest due to their unique transverse geometry and potential advantages. Here, we report the observation of a significant transverse thermoelectric conductivity alpha A_zx of 15 A K-1m-1 at low temperatures, together with a pronounced anomalous Nernst effect in the Kagome antiferromagnet FeGe, which exhibits a charge density wave inside the antiferromagnetic (AFM) state. This value is the highest record among known AFM materials. Furthermore, the thermopower at 14 T increases by 102-104% around the canted-AFM (CAFM) transition temperature, Tcant, comparable to that of the well-known AFM thermoelectric materials. These effects are attributed to large Berry curvature arising from the non-collinear spin texture in FeGe, highlighting its potential for enhancing thermoelectric performance and its candidacy for magneto-TE applications in Kagome antiferromagnetic materials.

cond-mat.mtrl-sci↗

arXiv2025

Threshold Tensor Factor Model in CP Form

This paper proposes a new Threshold Tensor Factor Model in Canonical Polyadic (CP) form for tensor time series. By integrating a thresholding autoregressive structure for the latent factor process into the tensor factor model in CP form, the model captures regime-switching dynamics in the latent factor processes while retaining the parsimony and interpretability of low-rank tensor representations. We develop estimation procedures for the model and establish the theoretical properties of the resulting estimators. Numerical experiments and a real-data application illustrate the practical performance and usefulness of the proposed framework.

stat.ME↗

arXiv2025

Unbiased Platform-Level Causal Estimation for Search Systems: A Competitive Isolation PSM-DID Framework

Evaluating platform-level interventions in search-based two-sided marketplaces is fundamentally challenged by systemic effects such as spillovers and network interference. While widely used for causal inference, the PSM (Propensity Score Matching) - DID (Difference-in-Differences) framework remains susceptible to selection bias and cross-unit interference from unaccounted spillovers. In this paper, we introduced Competitive Isolation PSM-DID, a novel causal framework that integrates propensity score matching with competitive isolation to enable platform-level effect measurement (e.g., order volume, GMV) instead of item-level metrics in search systems. Our approach provides theoretically guaranteed unbiased estimation under mutual exclusion conditions, with an open dataset released to support reproducible research on marketplace interference (github.com/xxxx). Extensive experiments demonstrate significant reductions in interference effects and estimation variance compared to baseline methods. Successful deployment in a large-scale marketplace confirms the framework's practical utility for platform-level causal inference.

cs.AI↗

arXiv2025

A generalization of the Mordell integral

We find a generalization of the Mordell integral and we also establish a set of properties for a generalization of the Mordell integral similar to those in the third author's PhD thesis.

math.NT↗

arXiv2025

KunServe: Parameter-centric Memory Management for Efficient Memory Overloading Handling in LLM Serving

Serving LLMs with a cluster of GPUs is common nowadays, where the serving system must meet strict latency SLOs required by applications. However, the stateful nature of LLM serving requires maintaining huge states (i.e., KVCache) in limited GPU memory. Under spikes in real-world workloads, GPU memory can be easily throttled, leading to orders of magnitude higher response latency due to queuing introduced by waiting for KVCache to be reclaimed. Prior KVCache-centric approaches handle load throttling by dropping, migrating, or swapping KVCache. These methods fail to release sufficient memory quickly with requests still queued. This paper proposes the first parameter-centric approach to handling throttling by selectively dropping replicated parameters to instantly free memory for requests, based on an unnoticed observation that model parameters are commonly replicated across GPUs for serving LLMs. With additional memory, all requests can be served with a larger batch without queuing. To make the parameter-centric approach correct and efficient, we cooperatively execute requests on GPUs with a complete copy of parameters using pipeline parallelism, and derive an appropriate drop plan without unnecessary cooperation. We also design techniques to minimize the performance overhead due to pipeline parallelism with the execution patterns of requests under drop. Evaluations show that {\sys} reduces the tail TTFT of requests under throttling by up to 72.2 times compared to the state-of-the-art systems including Llumnix, vLLM and InferCept.

cs.DC↗

arXiv2025

ProMoE: Fast MoE-based LLM Serving using Proactive Caching

The promising applications of large language models are often limited by the constrained GPU memory capacity available on edge devices. Mixture-of-Experts (MoE) models help address this issue by activating only a subset of the model's parameters during computation. This approach allows the unused parameters to be offloaded to host memory, thereby reducing the overall GPU memory demand. However, existing cache-based offloading solutions handle cache misses reactively, which significantly impacts system performance. In this paper, we introduce ProMoE, a novel proactive caching system that utilizes intermediate results to predict subsequent expert usage. By proactively fetching experts in advance, ProMoE eliminates passive cache misses, removes loading time from the critical path, and reduces the performance overhead associated with offloading. Our evaluations demonstrate that ProMoE achieves an average speedup of 2.20x (up to 3.21x) and 2.07x (up to 5.02x) in the prefill and decode stages, respectively, compared to existing offloading solutions.

cs.DC↗

arXiv2025

Graphs with girth $2\ell$ and without longer even holes are $3$-colorable

For a number $\ell\geq 2$, let $\mathcal{H}_{\ell}$ denote the family of graphs which have girth $2\ell$ and have no even hole with length greater than $2\ell$. Wu, Xu, and Xu conjectured that every graph in $\bigcup_{\ell\geq2}\mathcal{H}_{\ell}$ is 3-colorable. In this paper, we prove that every graph in $\mathcal{H}_{\ell}$ is 3-colorable for any integer $\ell\geq5$.

math.CO↗

arXiv2025

PhoenixOS: Concurrent OS-level GPU Checkpoint and Restore with Validated Speculation

PHOENIXOS (PHOS) is the first OS service that can concurrently checkpoint and restore (C/R) GPU processes--a fundamental capability for critical tasks such as fault tolerance, process migration, and fast startup. While concurrent C/R is well-established on CPUs, it poses unique challenges on GPUs due to their lack of essential features for efficiently tracing concurrent memory reads and writes, such as specific hardware capabilities (e.g., dirty bits) and OS-mediated data paths (e.g., copy-on-write). To ensure correct concurrent C/R, PHOS proactively detects GPU memory reads and writes through a two-step process: first, it speculates about GPU memory accesses based on the arguments used when launching GPU kernels; then, it validates these accesses efficiently at runtime using binary instrumentation. With this validated speculation, PHOS retrofits CPU-based concurrent C/R for GPUs through software-based approaches, including soft copy-on-write, soft recopy, and soft on-demand restore. PHOS further proposes several GPU-aware techniques for efficient GPU C/R, including coordinated checkpoint data transfer and execution context pool. For downstream tasks that use C/R for tolerating failures, migrating processes between machines, and accelerating cold starts in serverless computing, PHOS achieves orders of magnitude higher performance than state-of-the-art OS-level GPU C/R systems like NVIDIA cuda-checkpoint.

cs.DC↗

arXiv2025

Holistic Heterogeneous Scheduling for Autonomous Applications using Fine-grained, Multi-XPU Abstraction

Modern autonomous applications are increasingly utilizing multiple heterogeneous processors (XPUs) to accelerate different stages of algorithm modules. However, existing runtime systems for these applications, such as ROS, can only perform module-level task management, lacking awareness of the fine-grained usage of multiple XPUs. This paper presents XAUTO, a runtime system designed to cooperatively manage XPUs for latency-sensitive autonomous applications. The key idea is a fine-grained, multi-XPU programming abstraction -- XNODE, which aligns with the stage-level task granularity and can accommodate multiple XPU implementations. XAUTO holistically assigns XPUs to XNODEs and schedules their execution to minimize end-to-end latency. Experimental results show that XAUTO can reduce the end-to-end latency of a perception pipeline for autonomous driving by 1.61x compared to a state-of-the-art module-level scheduling system (ROS2).

cs.OS↗

arXiv2025

Towards Lock Modularization for Heterogeneous Environments

Modern hardware environments are becoming increasingly heterogeneous, leading to the emergence of applications specifically designed to exploit this heterogeneity. Efficiently adopting locks in these applications poses distinct challenges. The uneven distribution of resources in such environments can create bottlenecks for lock operations, severely hindering application performance. Existing solutions are often tailored to specific types of hardware, which underutilizes resources on other components within heterogeneous environments. This paper introduces a new design principle: decomposing locks across hardware components to fully utilize unevenly distributed resources in heterogeneous environments. Following this principle, we propose lock modularization, a systematic approach that decomposes a lock into independent modules and assigns them to appropriate hardware components. This approach aligns the resource requirements of lock modules with the attributes of specific hardware components, maximizing strengths while minimizing weaknesses.

cs.DC↗

arXiv2025

BLITZSCALE: Fast and Live Large Model Autoscaling with O(1) Host Caching

Model autoscaling is the key mechanism to achieve serverless model-as-a-service, but it faces a fundamental trade-off between scaling speed and storage/memory usage to cache parameters, and cannot meet frequent scaling requirements across multiple hosts. The key problem is that data plane performance is slow, and scaled instances remain stopped while parameters are loading. In this paper, we first show that the data plane can be made fast with no or O(1) caching by loading parameters through the compute network between GPUs because: (1) its speed is comparable to host cache and is underutilized, and (2) scaling multiple instances requires no or O(1) caching with network-optimized multicast. Second, autoscaling can be made live by breaking the scaling abstraction for inference from a coarse-grained instance-level to a fine-grained layer-level. This allows us to offload the layer computation from the overloaded serving instances to the scaled ones without waiting for the parameters to be fully loaded. Under real-world workloads, our system BLITZSCALE achieves up to 94 % lower tail latency reductions compared to state-of-the-art autoscaling system (ServerlessLLM), and it reduces the GPU time used for serving by 49 % when compared with serving systems that do not support autoscaling like DistServe and vLLM with the same service-level-agreement.

cs.DC↗

arXiv2025

hqQUBO: A Hybrid-querying Quantum Optimization Model Validated with 16-qubits on an Ion Trap Quantum Computer for Life Science Applications

AlphaFold has achieved groundbreaking advancements in protein structure prediction, exerting profound influence across biology, medicine, and drug discovery. However, its reliance on multiple sequence alignment (MSA) is inherently time-consuming due to the NP-hard nature of constructing MSAs. Quantum computing emerges as a promising alternative, compared to classical computers, offering the potentials for exponential speedup and improved accuracy on such complex optimization challenges. This work bridges the gap between quantum computing and MSA task efficiently and successfully, where we compared classical and quantum computational scaling as the number of qubits increases, and assessed the role of quantum entanglement in model performance. Furthermore, we proposed an innovative hybrid query encoding approach hyQUBO to avoid redundancy, and thereby the quantum resources significantly reduced to a scaling of $\mathcal{O}(NL)$. Additionally, coupling of VQE and the quenched CVaR scheme was utilized to enhance the robustness and convergence. The integration of multiple strategies facilitates the robust deployment of the quantum algorithm from idealized simulators (on CPU and GPU) to real-world, noisy quantum devices (HYQ-A37). To the best of our knowledge, our work represented the largest-scale implementation of digital simulation using up to 16 qubits on a trapped-ion quantum computer for life science problem, which achieved state of the art performance in both simulation and experimental results. Our work paves the way towards large-scale simulations of life science tasks on real quantum processors.

quant-ph↗

arXiv2025

DecLock: A Case of Decoupled Locking for Disaggregated Memory

This paper reveals that locking can significantly degrade the performance of applications on disaggregated memory (DM), sometimes by several orders of magnitude, due to contention on the NICs of memory nodes (MN-NICs). To address this issue, we present DecLock, a locking mechanism for DM that employs decentralized coordination for ownership transfer across compute nodes (CNs) while retaining centralized state maintenance on memory nodes (MNs). DecLock features cooperative queue-notify locking that queues lock waiters on MNs atomically, enabling clients to transfer lock ownership via message-based notifications between CNs. This approach conserves MN-NIC resources for DM applications and ensures fairness. Evaluations show DecLock achieves throughput improvements of up to 43.37$\times$ and 1.81$\times$ over state-of-the-art RDMA-based spinlocks and MCS locks, respectively. Furthermore, DecLock helps two DM applications, including an object store and a real-world database index (Sherman), avoid performance degradation under high contention, improving throughput by up to 35.60$\times$ and 2.31$\times$ and reducing 99th-percentile latency by up to 98.8% and 82.1%.

cs.DC↗

arXiv2025

DiFache: Efficient and Scalable Caching on Disaggregated Memory using Decentralized Coherence

The disaggregated memory (DM) architecture offers high resource elasticity at the cost of data access performance. While caching frequently accessed data in compute nodes (CNs) reduces access overhead, it requires costly centralized maintenance of cache coherence across CNs. This paper presents DiFache, an efficient, scalable, and coherent CN-side caching framework for DM applications. Observing that DM applications already serialize conflicting remote data access internally rather than relying on the cache layer, DiFache introduces decentralized coherence that aligns its consistency model with memory nodes instead of CPU caches, thereby eliminating the need for centralized management. DiFache features a decentralized invalidation mechanism to independently invalidate caches on remote CNs and a fine-grained adaptive scheme to cache objects with varying read-write ratios. Evaluations using 54 real-world traces from Twitter show that DiFache outperforms existing approaches by up to 10.83$\times$ (5.53$\times$ on average). By integrating DiFache, the peak throughput of two real-world DM applications increases by 7.94$\times$ and 2.19$\times$, respectively.

cs.DC↗

arXiv2025

Combinatorial proofs for partitions with repeated smallest part

Recently, Andrews and El Bachraoui considered the number of integer partitions whose smallest part is repeated exactly $k$ times and the remaining parts are not repeated. They presented several interesting results and posed questions regarding combinatorial proofs for these identities. In this paper, we establish bijections to provide combinatorial proofs for these results.

math.CO↗