| 1. |
- haghifam, mahdi, et al.
(author)
-
Joint Sum Rate and Error Probability Optimization: Finite Blocklength Analysis
- 2017
-
In: IEEE Wireless Communications Letters. - 2162-2345 .- 2162-2337. ; 6:6, s. 726-729
-
Journal article (peer-reviewed)abstract
- We study the tradeoff between the sum rate and the error probability in downlink of wireless networks. Using the recent results on the achievable rates of finite-length codewords, the problem is cast as a joint optimization of the network sum rate and the per-user error probability. We develop an efficient algorithm based on the divide-and-conquer technique to simultaneously maximize the network sum rate and minimize the maximum users’ error probability and to evaluate the effect of the codeword length on the system performance. The results show that, in delay-constrained scenarios, optimizing the per-user error probability plays a key role in achieving high throughput.
|
|
| 2. |
- Haghifam, Mahdi, et al.
(author)
-
Limitations of information : theoretic generalization bounds for gradient descent methods in stochastic convex optimization
- 2023
-
In: Proceedings of ALT 2023. - : ML Research Press. ; , s. 663-706
-
Conference paper (peer-reviewed)abstract
- To date, no “information-theoretic” frameworks for reasoning about generalization error have been shown to establish minimax rates for gradient descent in the setting of stochastic convex optimization. In this work, we consider the prospect of establishing such rates via several existing information-theoretic frameworks: input-output mutual information bounds, conditional mutual information bounds and variants, PAC-Bayes bounds, and recent conditional variants thereof. We prove that none of these bounds are able to establish minimax rates. We then consider a common tactic employed in studying gradient methods, whereby the final iterate is corrupted by Gaussian noise, producing a noisy “surrogate” algorithm. We prove that minimax rates cannot be established via the analysis of such surrogates. Our results suggest that new ideas are required to analyze gradient descent using information-theoretic techniques.
|
|
| 3. |
- Haghifam, Mahdi R., et al.
(author)
-
On joint energy and information transfer in relay networks with an imperfect power amplifier
- 2016
-
In: 27th IEEE Annual International Symposium on Personal, Indoor, and Mobile Radio Communications, PIMRC 2016; Valencia; Spain; 4-8 September, 2016. - 9781509032549 ; , s. Art no 7794872-
-
Conference paper (peer-reviewed)abstract
- This paper investigates the outage probability and the throughput of relay networks with joint information and energy transfer where the relay harvests energy from transmitted radio-frequency (RF) signal of the source. Considering different power consumption models, we derive the outage probability of the systems for both adaptive and non-adaptive power allocations at the relay. With a total energy consumption constraint at the source, we provide closed-form expressions for the optimal time sharing and power allocation between the source energy and information transfer signals. The analytical and simulation results demonstrate the efficiency of joint energy and information transfer systems in different conditions
|
|
