With the increasing demands on interactive video applications, how to adapt video bit rate to avoid network congestion has become critical, since congestion results in selfinflicted delay and packet loss which deteriorate the quality of real-time video service. The existing congestion control is hard to simultaneously achieve low latency, high throughput, good adaptability and fair bandwidth allocation, mainly because of the hardwired control strategy and egocentric convergence objective.To address these issues, we propose an end-to-end statistical learning based congestion control, named Iris. By exploring the underlying principles of self-inflicted delay, we reveal that congestion delay is determined by sending rate, receiving rate and network status, which inspires us to control video bit rate using a statistical-learning congestion control model. The key idea of Iris is to force all flows to converge to the same queue load, and adjust the bit rate by the model. All flows keep a small and fixed number of packets queuing in the network, thus the fair bandwidth allocation and low latency are both achieved. Besides, the adjustment step size of sending rate is updated by online learning, to better adapt to dynamically changing networks.We carried out extensive experiments to evaluate the performance of Iris, with the implementations of transport layer (UDP) and application layer (QUIC) respectively. The testing environment includes emulated network, real-world Internet and commercial LTE networks. Compared against TCP flavors and state-of-the-art protocols, Iris is able to achieve high bandwidth utilization, low latency and good fairness concurrently. Especially over QUIC, Iris is able to increase the video bitrate up to 25%, and PSNR up to 1dB.Index Terms-Congestion control, real-time video streaming, low latency, statistical learning, adaptive adjustment.• Non-coexistence of high throughput and low latency.Considering only packet loss will lead to high queuing delay, but the algorithms overly concerned about delay also lead to low throughput [25]. • Hardwired control strategy. Most methods adjust sending rate with fixed step size or multiplier [26]. This manual mapping cannot always be optimal in changing networks, resulting in performance degradation. • Egocentric convergence objective. Some algorithms based on objective function are self-centered and lack communication between concurrent data streams, thus thye can not keep the same convergence goal for different clients, which leads to unfair bandwidth allocation.Motivated by these issues, to obtain higher video transmission quality, we probe into the essence of congestion control and consider whether it is possible to design an algorithm that achieves the goals of low latency, high channel utilization, good adaptability to changing networks and fair bandwidth allocation. Some recently proposed algorithms [27, 28] have enlightened us: a congestion control with low-latency fairness arXiv:1905.05998v2 [cs.MM]