Now 5229 visitors
Today:0 Yesterday:0
Total: 147754
212S 50P 4R
2026-10-20, Week 43 |
| Member Login |
| TACT Journal Homepage |
| Call for Paper |
| Committee |
| Find My Paper |
| Author Homepage |
| Statistics & History |
| Welcome Message |
| Paper Procedure |
| FAQ |
| Paper Archives |
| Outstanding Papers |
| Author Homepage |
| - Paper Procedure |
| - Journal Procedure |
| - Presentation Tips |
|
| Program & Proceedings |
| Program with Papers |
| Plenary Session |
| Tutorial Session |
|
| Presentation Platform |
| Hotel & Travel Info |
| About Korea |
| Accommodation |
| Transportation |
| VISA |
| Other Infomation |
|
| Photo Gallery |
| Scheduler Login |
| Seminar |
| Archives Login |
|
| Sponsors |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| Save Q&A |
 |
* Edit or answer any Q&A by selecting Q&A number Hyper Link below + Write button (Save)
|
ICACT20260127 Question.1
Questioner: mrajhans@paloaltonetworks.com 2026-02-15 오후 12:52:04 |
ICACT20260127 Answer.1
Answer by Auhor afaq24@gmail.com 2026-02-15 오후 12:52:04
Chrome  Click!! |
| Given that the hybrid QSVM underperforms Random Forest substantially in accuracy, how does the proposed framework justify practical deployment, and under what workload dynamics (e.g., retraining frequency, feature drift, or dataset scale) does the quantum component provide a net advantage over classical baselines? |
That’s a very fair question, and we agree with the premise. In our current experiments, Random Forest clearly outperforms the hybrid QSVM in terms of raw accuracy, and we do not claim otherwise. Our framework is not proposing to replace strong classical baselines, but to augment them under specific operational conditions.
The motivation for the quantum component is not higher accuracy on static datasets, but its potential role under dynamic cloud workloads. In environments where workload characteristics change frequently and retraining is required often, the amortized training behavior of kernel-based models becomes relevant. Once quantum kernels are computed, QSVM fitting can be relatively fast, which may be beneficial in frequent retraining scenarios.
Additionally, we observe that the hybrid QSVM maintains strong discriminative capability, with a ROC AUC of 0.88, indicating that it captures nonlinear feature interactions effectively. This can be valuable in cases where job failures arise from complex interactions among resource and scheduling features.
Practically, our framework is modular and supports adaptive α tuning. In deployment, the quantum contribution can be increased or reduced depending on workload dynamics, feature drift, and operational constraints. As quantum hardware and kernel evaluation mature, this hybrid design allows incremental adoption rather than disruptive replacement. |
ICACT20260127 Question.2
Questioner: gonghao23@mails.ucas.ac.cn 2026-02-23 오후 11:33:17 |
ICACT20260127 Answer.2
Answer by Auhor afaq24@gmail.com 2026-02-23 오후 11:33:17
Chrome Click!! |
| On the scalability of the hybrid kernel approach: The paper fixes α = 0.5 for blending the RBF and quantum kernels, but only evaluates on 5,000 samples. How would the optimal α value shift as dataset size scales to hundreds of thousands of samples, and could an adaptive α tuned per workload distribution yield meaningful accuracy gains for the Hybrid QSVM? |
|
ICACT20260127 Question.3
Questioner: gonghao23@mails.ucas.ac.cn 2026-02-23 오후 11:33:34 |
ICACT20260127 Answer.3
Answer by Auhor afaq24@gmail.com 2026-02-23 오후 11:33:34
Chrome Click!! |
| On the fairness of the timing comparison: The paper reports fit-time costs while explicitly excluding quantum kernel precomputation overhead for the QSVM. Given that kernel precomputation is an unavoidable part of the full inference pipeline in production cloud environments, how should total wall-clock latency — including precomputation — be factored into the efficiency trade-off argument, and does the claimed retraining advantage of the hybrid model still hold under that more complete accounting? |
|
| |
