Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
143 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Timely Communications for Remote Inference (2404.16281v2)

Published 25 Apr 2024 in cs.NI, cs.IT, cs.LG, and math.IT

Abstract: In this paper, we analyze the impact of data freshness on remote inference systems, where a pre-trained neural network blue infers a time-varying target (e.g., the locations of vehicles and pedestrians) based on features (e.g., video frames) observed at a sensing node (e.g., a camera). One might expect that the performance of a remote inference system degrades monotonically as the feature becomes stale. Using an information-theoretic analysis, we show that this is true if the feature and target data sequence can be closely approximated as a Markov chain, whereas it is not true if the data sequence is far from being Markovian. Hence, the inference error is a function of Age of Information (AoI), where the function could be non-monotonic. To minimize the inference error in real-time, we propose a new "selection-from-buffer" model for sending the features, which is more general than the "generate-at-will" model used in earlier studies. In addition, we design low-complexity scheduling policies to improve inference performance. For single-source, single-channel systems, we provide an optimal scheduling policy. In multi-source, multi-channel systems, the scheduling problem becomes a multi-action restless multi-armed bandit problem. For this setting, we design a new scheduling policy by integrating Whittle index-based source selection and duality-based feature selection-from-buffer algorithms. This new scheduling policy is proven to be asymptotically optimal. These scheduling results hold for minimizing general AoI functions (monotonic or non-monotonic). Data-driven evaluations demonstrate the significant advantages of our proposed scheduling policies.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (54)
  1. M. K. C. Shisher and Y. Sun, “How does data freshness affect real-time supervised learning?” ACM MobiHoc, 2022.
  2. X. Song and J. W.-S. Liu, “Performance of multiversion concurrency control algorithms in maintaining temporal consistency,” in Fourteenth Annual International Computer Software and Applications Conference.   IEEE, 1990, pp. 132–133.
  3. S. Kaul, R. Yates, and M. Gruteser, “Real-time status: How often should one update?” in IEEE INFOCOM, 2012, pp. 2731–2735.
  4. R. D. Yates, “Lazy is timely: Status updates by an energy harvesting source,” in IEEE ISIT, 2015, pp. 3008–3012.
  5. Y. Sun, E. Uysal-Biyikoglu, R. D. Yates, C. E. Koksal, and N. B. Shroff, “Update or wait: How to keep your data fresh,” IEEE Trans. Inf. Theory, vol. 63, no. 11, pp. 7492–7508, 2017.
  6. Y. Sun, E. Uysal-Biyikoglu, R. Yates, C. E. Koksal, and N. B. Shroff, “Update or wait: How to keep your data fresh,” in IEEE INFOCOM, 2016, pp. 1–9.
  7. Y. Sun and B. Cyr, “Sampling for data freshness optimization: Non-linear age functions,” J. Commun. Netw., vol. 21, no. 3, pp. 204–219, 2019.
  8. ——, “Information aging through queues: A mutual information perspective,” in Proc. IEEE SPAWC Workshop, 2018.
  9. T. Z. Ornee and Y. Sun, “Sampling and remote estimation for the ornstein-uhlenbeck process through queues: Age of information and beyond,” IEEE/ACM Trans. on Netw., vol. 29, no. 5, pp. 1962–1975, 2021.
  10. V. Tripathi and E. Modiano, “A Whittle index approach to minimizing functions of age of information,” in IEEE Allerton, 2019, pp. 1160–1167.
  11. M. Klügel, M. H. Mamduhi, S. Hirche, and W. Kellerer, “AoI-penalty minimization for networked control systems with packet loss,” in IEEE INFOCOM Age of Information Workshop, 2019, pp. 189–196.
  12. A. M. Bedewy, Y. Sun, S. Kompella, and N. B. Shroff, “Optimal sampling and scheduling for timely status updates in multi-source networks,” IEEE Trans. Inf. Theory, vol. 67, no. 6, pp. 4019–4034, 2021.
  13. I. Kadota, A. Sinha, and E. Modiano, “Optimizing age of information in wireless networks with throughput constraints,” in IEEE INFOCOM, 2018, pp. 1844–1852.
  14. Y. Hsu, “Age of information: Whittle index for scheduling stochastic arrivals,” in ISIT, 2018, pp. 2634–2638.
  15. J. Sun, Z. Jiang, B. Krishnamachari, S. Zhou, and Z. Niu, “Closed-form Whittle’s index-enabled random access for timely status update,” IEEE Transactions on Communications, vol. 68, no. 3, pp. 1538–1551, 2019.
  16. I. Kadota, A. Sinha, E. Uysal-Biyikoglu, R. Singh, and E. Modiano, “Scheduling policies for minimizing age of information in broadcast wireless networks,” IEEE/ACM Trans. Netw., vol. 26, no. 6, pp. 2637–2650, 2018.
  17. I. M. Verloop, “Asymptotically optimal priority policies for indexable and nonindexable restless bandits,” The Annals of Applied Probability, vol. 26, no. 4, p. 1947–1995, 2016.
  18. N. Gast, B. Gaujal, and C. Yan, “LP-based policies for restless bandits: necessary and sufficient conditions for (exponentially fast) asymptotic optimality,” Mathematics of Operations Research, pp. 1–29, 2023.
  19. A. X. Lee, R. Zhang, F. Ebert, P. Abbeel, C. Finn, and S. Levine, “Stochastic adversarial video prediction,” arXiv:1804.01523, 2018.
  20. C. Kam, S. Kompella, G. D. Nguyen, and A. Ephremides, “Effect of message transmission path diversity on status age,” IEEE Trans. Inf. Theory, vol. 62, no. 3, pp. 1360–1374, March 2016.
  21. T. Soleymani, S. Hirche, and J. S. Baras, “Optimal self-driven sampling for estimation based on value of information,” in IEEE WODES, 2016, pp. 183–188.
  22. G. Chen, S. C. Liew, and Y. Shao, “Uncertainty-of-information scheduling: A restless multiarmed bandit framework,” IEEE Trans. Inf. Theory, vol. 68, no. 9, pp. 6151–6173, 2022.
  23. Z. Wang, M.-A. Badiu, and J. P. Coon, “A framework for characterising the value of information in hidden Markov models,” IEEE Trans. Inf. Theory, 2022.
  24. T. Z. Ornee and Y. Sun, “A Whittle index policy for the remote estimation of multiple continuous Gauss-Markov processes over parallel channels,” ACM MobiHoc, 2023.
  25. J. Pan, Y. Sun, and N. B. Shroff, “Sampling for remote estimation of the wiener process over an unreliable channel,” ACM Sigmetrics, 2023.
  26. Y. Sun and S. Kompella, “Age-optimal multi-flow status updating with errors: A sample-path approach,” J. Commun. Netw., vol. 25, no. 5, pp. 570–584, 2023.
  27. R. D. Yates, Y. Sun, D. R. Brown, S. K. Kaul, E. Modiano, and S. Ulukus, “Age of information: An introduction and survey,” IEEE J. Select. Areas in Commun., vol. 39, no. 5, pp. 1183–1210, 2021.
  28. P. Whittle, “Restless bandits: Activity allocation in a changing world,” Journal of applied probability, vol. 25, no. A, pp. 287–298, 1988.
  29. T. Z. Ornee and Y. Sun, “Performance bounds for sampling and remote estimation of gauss-markov processes over a noisy channel with random delay,” in IEEE SPAWC, 2021.
  30. Y. Sun, Y. Polyanskiy, and E. Uysal, “Sampling of the Wiener process for remote estimation over a channel with random delay,” IEEE Trans. Inf. Theory, vol. 66, no. 2, pp. 1118–1135, 2020.
  31. G. Brockman, V. Cheung, L. Pettersson, J. Schneider, J. Schulman, J. Tang, and W. Zaremba, “Openai gym,” arXiv:1606.01540, 2016.
  32. P. D. Grünwald and A. P. Dawid, “Game theory, maximum entropy, minimum discrepancy and robust Bayesian decision theory,” Annals of Statistics, vol. 32, no. 4, pp. 1367–1433, 08 2004.
  33. A. P. Dawid, “Coherent measures of discrepancy, uncertainty and dependence, with applications to Bayesian predictive experimental design,” Technical Report 139, 1998.
  34. F. Farnia and D. Tse, “A minimax approach to supervised learning,” NIPS, vol. 29, pp. 4240–4248, 2016.
  35. M. K. C. Shisher, T. Z. Ornee, and Y. Sun, “A local geometric interpretation of feature extraction in deep feedforward neural networks,” arXiv:2202.04632, 2022.
  36. I. S. Dhillon and J. A. Tropp, “Matrix nearness problems with bregman divergences,” SIAM Journal on Matrix Analysis and Applications, vol. 29, no. 4, pp. 1120–1146, 2008.
  37. I. Csiszár and P. C. Shields, “Information theory and statistics: A tutorial,” 2004.
  38. S.-L. Huang, A. Makur, G. W. Wornell, and L. Zheng, “On universal features for high-dimensional learning and inference,” accepted to Foundations and Trends in Communications and Information Theory: Now Publishers, 2019, available in arXiv:1911.09105.
  39. Y. Polyanskiy and Y. Wu, “Lecture notes on information theory,” Lecture Notes for MIT (6.441), UIUC (ECE 563), Yale (STAT 664), no. 2012-2017, 2014.
  40. M. K. C. Shisher, H. Qin, L. Yang, F. Yan, and Y. Sun, “The age of correlated features in supervised learning based forecasting,” in IEEE INFOCOM Age of Information Workshop, 2021.
  41. C. E. Shannon, “A mathematical theory of communication,” The Bell system technical journal, vol. 27, no. 3, pp. 379–423, 1948.
  42. M. K. C. Shisher, B. Ji, I. Hou, and Y. Sun, “Learning and communications co-design for remote inference systems: Feature length selection and transmission scheduling,” IEEE J. Select. Areas in Inf. Theory, 2023.
  43. M. K. C. Shisher and Y. Sun, “On the monotonicity of information aging,” IEEE INFOCOM ASoI Workshop, 2024.
  44. M. N. Katehakis and A. F. Veinott Jr, “The multi-armed bandit problem: decomposition and computation,” Mathematics of Operations Research, vol. 12, no. 2, pp. 262–268, 1987.
  45. C. H. Papadimitriou and J. N. Tsitsiklis, “The complexity of optimal queueing network control,” in Proceedings of IEEE 9th Annual Conference on Structure in Complexity Theory, 1994, pp. 318–322.
  46. D. P. Palomar and M. Chiang, “A tutorial on decomposition methods for network utility maximization,” IEEE J. Select. Areas in Commun., vol. 24, no. 8, pp. 1439–1451, 2006.
  47. F. Ebert, C. Finn, A. Lee, and S. Levine, “Self-supervised visual planning with temporal skip connections,” in CoRL, 2017.
  48. D. Berenson, S. S. Srinivasa, D. Ferguson, A. Collet, and J. J. Kuffner, “Manipulation planning with workspace goal regions,” in 2009 IEEE international conference on robotics and automation.   IEEE, 2009, pp. 618–624.
  49. V. Mnih, K. Kavukcuoglu, D. Silver et al., “Human-level control through deep reinforcement learning,” nature, vol. 518, no. 7540, pp. 529–533, 2015.
  50. P. Attri, Y. Sharma, K. Takach, Shah, and Falak, “Timeseries forecasting for weather prediction,” 2020, online: https://keras.io/examples/timeseries/timeseries_weather_forecasting/.
  51. K. E. Baddour and N. C. Beaulieu, “Autoregressive modeling for fading channel simulation,” IEEE Trans. Wireless Commun., vol. 4, no. 4, pp. 1650–1662, 2005.
  52. J. Liao, O. Kosut, L. Sankar, and F. P. Calmon, “A tunable measure for information leakage,” in IEEE ISIT, 2018, pp. 701–705.
  53. S.-I. Amari, “α𝛼\alphaitalic_α -divergence is unique, belonging to both f𝑓fitalic_f-divergence and bregman divergence classes,” IEEE Trans. Inf. Theory, vol. 55, no. 11, pp. 4925–4931, 2009.
  54. N. Gast, B. Gaujal, and C. Yan, “Exponential asymptotic optimality of whittle index policy,” Queueing Systems, vol. 104, no. 1, pp. 107–150, 2023.
Citations (8)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now