Timely Communications for Remote Inference
Pages 3824 - 3839
Abstract
In this paper, we analyze the impact of data freshness on remote inference systems, where a pre-trained neural network 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.
References
[1]
M. K. C. Shisher and Y. Sun, “How does data freshness affect real-time supervised learning?,” in Proc. ACM MobiHoc, 2022, pp. 31–40.
[2]
X. Song and J. W.-S. Liu, “Performance of multiversion concurrency control algorithms in maintaining temporal consistency,” in Proc. 14th Annu. Int. Comput. Softw. Appl. Conf., 1990, pp. 132–133.
[3]
S. Kaul, R. Yates, and M. Gruteser, “Real-time status: How often should one update?,” in Proc. IEEE INFOCOM, Mar. 2012, pp. 2731–2735.
[4]
R. D. Yates, “Lazy is timely: Status updates by an energy harvesting source,” in Proc. IEEE Int. Symp. Inf. Theory (ISIT), Jun. 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, Nov. 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 Proc. IEEE INFOCOM, Apr. 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, Jun. 2019.
[8]
Y. Sun and B. Cyr, “Information aging through queues: A mutual information perspective,” in Proc. IEEE 19th Int. Workshop Signal Process. Adv. Wireless Commun. (SPAWC), Jun. 2018, pp. 1–5.
[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. Netw., vol. 29, no. 5, pp. 1962–1975, Oct. 2021.
[10]
V. Tripathi and E. Modiano, “A whittle index approach to minimizing functions of age of information,” in Proc. 57th Annu. Allerton Conf. Commun., Control, Comput. (Allerton), Sep. 2019, pp. 1160–1167.
[11]
M. Klugel, M. H. Mamduhi, S. Hirche, and W. Kellerer, “AoI-penalty minimization for networked control systems with packet loss,” in Proc. IEEE Conf. Comput. Commun. Workshops (INFOCOM WKSHPS), 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, Jun. 2021.
[13]
I. Kadota, A. Sinha, and E. Modiano, “Optimizing age of information in wireless networks with throughput constraints,” in Proc. IEEE Conf. Comput. Commun. (INFOCOM), Apr. 2018, pp. 1844–1852.
[14]
Y. Hsu, “Age of information: Whittle index for scheduling stochastic arrivals,” in Proc. IEEE Int. Symp. Inf. Theory (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 Trans. Commun., vol. 68, no. 3, pp. 1538–1551, Mar. 2020.
[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, Dec. 2018.
[17]
I. M. Verloop, “Asymptotically optimal priority policies for indexable and nonindexable restless bandits,” Ann. Appl. Probab., vol. 26, no. 4, pp. 1947–1995, Aug. 2016.
[18]
N. Gast, B. Gaujal, and C. Yan, “LP-based policies for restless bandits: Necessary and sufficient conditions for (exponentially fast) asymptotic optimality,” Math. Operations Res., pp. 1–29, Dec. 2023. 10.1287/moor.2022.0101.
[19]
A. X. Lee, R. Zhang, F. Ebert, P. Abbeel, C. Finn, and S. Levine, “Stochastic adversarial video prediction,” 2018, arXiv:1804.01523.
[20]
M. K. Chowdhury Shisher, H. Qin, L. Yang, F. Yan, and Y. Sun, “The age of correlated features in supervised learning based forecasting,” in Proc. IEEE Conf. Comput. Commun. Workshops (INFOCOM WKSHPS), May 2021, pp. 1–8.
[21]
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, Mar. 2016.
[22]
T. Soleymani, S. Hirche, and J. S. Baras, “Optimal self-driven sampling for estimation based on value of information,” in Proc. 13th Int. Workshop Discrete Event Syst. (WODES), May 2016, pp. 183–188.
[23]
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, Sep. 2022.
[24]
Z. Wang, M.-A. Badiu, and J. P. Coon, “A framework for Characterizing the value of information in hidden Markov models,” IEEE Trans. Inf. Theory, vol. 68, no. 8, pp. 5203–5216, Aug. 2022.
[25]
T. Z. Ornee and Y. Sun, “A Whittle index policy for the remote estimation of multiple continuous Gauss-Markov processes over parallel channels,” in Proc. ACM MobiHoc, 2023, pp. 91–100.
[26]
J. Pan, Y. Sun, and N. B. Shroff, “Sampling for remote estimation of the Wiener process over an unreliable channel,” Proc. ACM Meas. Anal. Comput. Syst., vol. 7, no. 3, pp. 1–41, Dec. 2023.
[27]
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, Oct. 2023.
[28]
Y. Sun, I. Kadota, R. Talak, and E. Modiano, Age of Information: A New Metric for Information Freshness. Berlin, Germany: Springer Nature, 2022.
[29]
T. Z. Ornee, M. K. C. Shisher, C. Kam, and Y. Sun, “Context-aware status updating: Wireless scheduling for maximizing situational awareness in safety-critical systems,” in Proc. IEEE MILCOM, 2023, pp. 194–200.
[30]
O. Ayan, S. Hirche, A. Ephremides, and W. Kellerer, “Optimal finite horizon scheduling of wireless networked control systems,” IEEE/ACM Trans. Netw., vol. 32, no. 2, pp. 927–942, Apr. 2024.
[31]
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. Sel. Areas Commun., vol. 39, no. 5, pp. 1183–1210, May 2021.
[32]
P. Whittle, “Restless bandits: Activity allocation in a changing world,” J. Appl. Probab., vol. 25, pp. 287–298, Jan. 1988.
[33]
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 Proc. IEEE 22nd Int. Workshop Signal Process. Adv. Wireless Commun. (SPAWC), Sep. 2021, pp. 1–5.
[34]
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, Feb. 2020.
[35]
I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning. Cambridge, MA, USA: MIT Press, 2016.
[36]
G. Brockman et al., “OpenAI gym,” 2016, arXiv:1606.01540.
[37]
P. D. Grünwald and A. P. Dawid, “Game theory, maximum entropy, minimum discrepancy and robust Bayesian decision theory,” Ann. Statist., vol. 32, no. 4, pp. 1367–1433, Aug. 2004.
[38]
A. P. Dawid, “Coherent measures of discrepancy, uncertainty and dependence, with applications to Bayesian predictive experimental design,” Dept. Stat. Sci., Univ. College London, Tech. Rep. 139, 1998.
[39]
F. Farnia and D. Tse, “A minimax approach to supervised learning,” in Proc. NIPS, vol. 29, 2016, pp. 4240–4248.
[40]
M. K. C. Shisher, T. Z. Ornee, and Y. Sun, “A local geometric interpretation of feature extraction in deep feedforward neural networks,” 2022, arXiv:2202.04632.
[41]
I. S. Dhillon and J. A. Tropp, “Matrix nearness problems with Bregman divergences,” SIAM J. Matrix Anal. Appl., vol. 29, no. 4, pp. 1120–1146, Jan. 2008.
[42]
I. Csiszár and P. C. Shields, “Information theory and statistics: A tutorial,” in Foundations and Trends in Communications and Information Theory, vol. 1, no. 4. MA, USA: Now Publishers Inc., 2004. 10.1561/0100000004.
[43]
S.-L. Huang, A. Makur, G. W. Wornell, and L. Zheng, “Universal features for high-dimensional learning and inference,” in Foundations and Trends in Communications and Information Theory, vol. 21, nos. 1–2. MA, USA: Now Publishers Inc., 2024, pp. 1–299.
[44]
Y. Polyanskiy and Y. Wu, “Lecture notes on information theory,” Lect. Notes for MIT (6.441), UIUC (ECE 563), Yale (STAT 664), nos. 2012–2017, Tech. Rep., 2014. [Online]. Available: https://ocw.mit.edu/courses/6-441-information-theory-spring-2016/resources/mit6_441s16_course_notes/
[45]
T. M. Cover, Elements of Information Theory. Hoboken, NJ, USA: Wiley, 1999.
[46]
M. Shaked and J. G. Shanthikumar, Stochastic Orders. Berlin, Germany: Springer, 2007.
[47]
C. E. Shannon, “A mathematical theory of communication,” Bell Syst. Tech. J., vol. 27, no. 3, pp. 379–423, 1948.
[48]
M. K. C. Shisher, B. Ji, I.-H. Hou, and Y. Sun, “Learning and communications co-design for remote inference systems: Feature length selection and transmission scheduling,” IEEE J. Sel. Areas Inf. Theory, vol. 4, pp. 524–538, 2023.
[49]
M. K. C. Shisher and Y. Sun, “On the monotonicity of information aging,” in Proc. IEEE INFOCOM ASoI Workshop, 2024, pp. 1–12.
[50]
D. Bertsekas, Dynamic Programming and Optimal Control, vol. 1. Belmont, MA, USA: Athena Scientific, 2017.
[51]
J. Gittins, K. Glazebrook, and R. Weber, Multi-armed Bandit Allocation Indices. Hoboken, NJ, USA: Wiley, 2011.
[52]
M. N. Katehakis and A. F. Veinott, “The multi-armed bandit problem: Decomposition and computation,” Math. Operations Res., vol. 12, no. 2, pp. 262–268, May 1987.
[53]
C. H. Papadimitriou and J. N. Tsitsiklis, “The complexity of optimal queueing network control,” in Proc. IEEE 9th Annu. Conf. Struct. Complex. Theory, 1994, pp. 318–322.
[54]
D. P. Palomar and M. Chiang, “A tutorial on decomposition methods for network utility maximization,” IEEE J. Sel. Areas Commun., vol. 24, no. 8, pp. 1439–1451, Aug. 2006.
[55]
F. Ebert, C. Finn, A. X. Lee, and S. Levine, “Self-supervised visual planning with temporal skip connections,” 2017, arXiv:1710.05268.
[56]
D. Berenson, S. S. Srinivasa, D. Ferguson, A. Collet, and J. J. Kuffner, “Manipulation planning with workspace goal regions,” in Proc. IEEE Int. Conf. Robot. Autom., May 2009, pp. 618–624.
[57]
V. Mnih, “Human-level control through deep reinforcement learning,” Nature, vol. 518, pp. 529–533, Feb. 2015.
[58]
P. Attri, Y. Sharma, K. Takach, and F. Shah. (2020). Timeseries Forecasting for Weather Prediction. [Online]. Available: https://keras.io/examples/timeseries/timeseries_weather_forecasting/
[59]
K. E. Baddour and N. C. Beaulieu, “Autoregressive modeling for fading channel simulation,” IEEE Trans. Wireless Commun., vol. 4, no. 4, pp. 1650–1662, Jul. 2005.
[60]
J. Liao, O. Kosut, L. Sankar, and F. P. Calmon, “A tunable measure for information leakage,” in Proc. IEEE ISIT, Jun. 2018, pp. 701–705.
[61]
X.-D. Zhang, Matrix Analysis and Applications. Cambridge, U.K.: Cambridge Univ. Press, 2017.
[62]
S.-I. Amari, “α-Divergence is unique, belonging to both f-divergence and Bregman divergence classes,” IEEE Trans. Inf. Theory, vol. 55, no. 11, pp. 4925–4931, Nov. 2009.
[63]
R. Durrett, Probability: Theory and Examples, vol. 49. Cambridge, U.K.: Cambridge Univ. Press, 2019.
[64]
M. L. Puterman, Markov Decision Processes: Discrete Stochastic Dynamic Programming. Hoboken, NJ, USA: Wiley, 2014.
[65]
D. Bertsekas, A. Nedic, and A. Ozdaglar, Convex Analysis and Optimization, vol. 1. Belmont, MA, USA: Athena Scientific, 2003.
[66]
N. Gast, B. Gaujal, and C. Yan, “Exponential asymptotic optimality of whittle index policy,” Queueing Syst., vol. 104, nos. 1–2, pp. 107–150, Jun. 2023.
Index Terms
- Timely Communications for Remote Inference
Index terms have been assigned to the content through auto-classification.
Recommendations
Stochastic variational inference
We develop stochastic variational inference, a scalable algorithm for approximating posterior distributions. We develop this technique for a large class of probabilistic models and we demonstrate it with two probabilistic topic models, latent Dirichlet ...
Averaged collapsed variational bayes inference
This paper presents the Averaged CVB (ACVB) inference and oers convergence-guaranteed and practically useful fast Collapsed Variational Bayes (CVB) inferences. CVB inferences yield more precise inferences of Bayesian probabilistic models than ...
Post-inference prior swapping
ICML'17: Proceedings of the 34th International Conference on Machine Learning - Volume 70While Bayesian methods are praised for their ability to incorporate useful prior knowledge, in practice, convenient priors that allow for computationally cheap or tractable inference are commonly used. In this paper, we investigate the following ...
Comments
Information & Contributors
Information
Published In
1063-6692 © 2024 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. See https://www.ieee.org/publications/rights/index.html for more information.
Publisher
IEEE Press
Publication History
Published: 17 June 2024
Published in TON Volume 32, Issue 5
Qualifiers
- Research-article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 14Total Downloads
- Downloads (Last 12 months)14
- Downloads (Last 6 weeks)8
Reflects downloads up to 28 Dec 2024
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in