arXiv subjects

Hsiu-Chi Tsai

Publications and source records attributed to Hsiu-Chi Tsai.

3 recordsLinked to original sources

arXiv2026

Trusted Floors Under Untrusted Learners: A Runtime Assured-SLO Guard for ML Serving

Modern ML serving increasingly lets learned, unverified components (routers, latency-SLO admitters, admit ladders) decide a tenant's quality of service; when one is wrong, the assured SLO can silently break, and the Kubernetes layers beneath (Kueue, DRA, the Gateway-API Inference Extension, GAIE) add cross-layer surprises. Rather than trust the learner to be right, we bound the damage a wrong one can do: a small trusted guard wraps the untrusted learner (learned proposes, the guard disposes). A tenant's assured-SLO obligation splits into two parts with different epistemics. Its safety projection, a per-class, per-window assured floor (with an optional drop rule, doom-sound only under an assumed service lower envelope), is a controllable obligation a guard enforces at runtime, holding it regardless of a learned admitter that is arbitrarily wrong within a bounded proposal interface. The admission floor is enforced structurally; given the stated assumptions, the service floor follows as a conditional response-time implication. Its aggregate obligation (the population tail-latency percentile) has no per-request enforcement point, so we treat it as a statistical residual and screen it. On real 2xV100 the guard (a Simplex-style assured-floor gate plus assured-first priority) holds assured-class miss 0.0 across every tested miscalibration of a learned admitter that, unguarded, misses 0.86-0.94; against a live deployment of the GAIE Flow Control, an injected mapping fault (emulating an untrusted mapper) flips the same assured requests from miss 0.0 to 1.0 (a mechanism-level trust-boundary test, not a head-to-head), while our guard reserves by the true class. As a Frontiers submission we evaluate the stance on commodity 2xV100 and a serving simulator, scoping datacenter scale, real-model Flow Control, and a closed worst-case theorem as the agenda.

cs.DC↗

arXiv2026

Ground-Side Mission Plan Compilation with Policy-as-Code Guardrails for Cloud-Native Satellite Platforms

Onboard cloud-native runtimes for satellites are emerging on multiple tracks (ORCHIDE, Axiom Space's AxDCU-1, Kepler's Jetson nodes), but each assumes that the workflow artifacts it executes arrive from the ground. ORCHIDE's architecture document D3.1 states explicitly that "only the Deferred Phase is part of the ORCHIDE scope," and no open-source ground-side toolchain has been released by the consortium. We present Satellite Mission Compiler, a four-stage pipeline that addresses this gap: it takes a human-authored mission plan, checks it against machine-checkable structural and policy rules, and compiles it into the container-workflow artifacts that cloud-native satellite runtimes consume. The pipeline parses the plan against a Pydantic schema derived from public ORCHIDE materials, evaluates it against an OPA/Rego policy package of ten deny rules with documented provenance, compiles it into a typed WorkflowIntent intermediate representation, and renders it as Argo Workflow DAGs and Kueue Job manifests with Dynamic Resource Allocation (DRA) support. We classify pre-uplink loss events into four severity tiers tied to specific schema and policy checks, and anchor the layered-validation design in the safety reading of defense-in-depth (NASA-STD-8739.8B) rather than the security reading (NIST SP 800-53). The implementation is validated by golden translation evaluations, argo lint, an in-process baseline that reproduces OPA's decisions, and live single-node cluster submission, including a DRA-backed GPU admission cascade on Kueue v0.17.3 (re-validated on v0.18.3) and, on v0.18.3, a unified GPU+CPU device-class quota with a scheduler-level accelerator fallback. Six Model Context Protocol (MCP) tools expose the pipeline to AI agents. The compiler is released under EUPL-1.2 (DOI 10.5281/zenodo.21228150).

cs.DC↗

arXiv2026

An Iterative Dual-Channel Neural Quantum State Algorithm for Selected Configuration Interaction

Accurately solving the electronic Schrödinger equation for strongly correlated systems remains a central challenge in quantum chemistry, where the exponential growth of configuration space limits the applicability of exact methods. Selected Configuration Interaction (SCI) algorithms address this challenge by adaptively constructing compact determinantal expansions, yet their efficiency depends critically on the quality of the sampling strategy used to identify chemically important configurations. Here we introduce the Handover Iterative Neural Quantum State (HI-NQS) algorithm, which embeds a classically trained autoregressive Transformer neural quantum state within the iterative sample--diagonalize--update framework of Sample-Based Quantum Diagonalization. A dual-channel Transformer architecture with explicit spin-up/spin-down cross-attention encodes fermionic spin structure as an architectural inductive bias, enabling expressive and physically informed wavefunction representations. After each subspace diagonalization, the resulting eigenvector is distilled back into the network through a factorized spin-marginal teacher signal, establishing a closed feedback loop between generative sampling and exact diagonalization. Benchmarks across a range of small molecules and a systematic nitrogen active-space series demonstrate that HI-NQS achieves chemical accuracy on all systems tested, with determinant-count scaling substantially more favorable than conventional CIPSI-based SCI for all but the smallest active spaces. All calculations are performed on GPU hardware without quantum computing resources, establishing HI-NQS as an efficient and scalable purely classical approach to the selected configuration interaction problem.

physics.chem-ph↗