# CausalSim: A Causal Framework for Unbiased Trace-Driven Simulation

arXiv: https://arxiv.org/abs/2201.01811 · HTML: https://mlsanity.com/paper/2201.01811/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 78 references that are in the map.
- First posted on arXiv 5 Jan 2022.

## Builds on (most cited first, 15 of 15)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Adversarial Discriminative Domain Adaptation](https://mlsanity.com/paper/1702.05464/) (2017)
- [Causal Intervention for Weakly-Supervised Semantic Segmentation](https://mlsanity.com/paper/2009.12547/) (2020)
- [Counterfactual Fairness in Text Classification through Robustness](https://mlsanity.com/paper/1809.10610/) (2018)
- [Exact tensor completion using t-SVD](https://mlsanity.com/paper/1502.04689/) (2015)
- [ME-Net: Towards Effective Adversarial Robustness with Matrix Estimation](https://mlsanity.com/paper/1905.11971/) (2019)
- [Causal Matrix Completion](https://mlsanity.com/paper/2109.15154/) (2021)
- [Variance Reduction for Reinforcement Learning in Input-Driven Environments](https://mlsanity.com/paper/1807.02264/) (2018)
- [On Robustness of Principal Component Regression](https://mlsanity.com/paper/1902.10920/) (2019)
- [BOLA: Near-Optimal Bitrate Adaptation for Online Videos](https://mlsanity.com/paper/1601.06748/) (2016)
- [Synthetic Interventions](https://mlsanity.com/paper/2006.07691/) (2020)
- [Robust Synthetic Control](https://mlsanity.com/paper/1711.06940/) (2017)
- [PerSim: Data-Efficient Offline Reinforcement Learning with Heterogeneous Agents via Personalized Simulators](https://mlsanity.com/paper/2102.06961/) (2021)
- [Implementing BOLA-BASIC on Puffer: Lessons for the use of SSIM in ABR logic](https://mlsanity.com/paper/2011.09611/) (2020)

## Built on by (most cited first, 10 of 10)

- [Counterfactual Identifiability of Bijective Causal Models](https://mlsanity.com/paper/2302.02228/) (2023)
- [Tao: Re-Thinking DL-based Microarchitecture Simulation](https://mlsanity.com/paper/2404.10921/) (2024)
- [Causal DAG Summarization (Full Version)](https://mlsanity.com/paper/2504.14937/) (2025)
- [Demystifying Network Foundation Models](https://mlsanity.com/paper/2509.23089/) (2025)
- [Enabling robots to follow abstract instructions and complete complex dynamic tasks](https://mlsanity.com/paper/2406.11231/) (2024)
- [Silent Neuron Theory and Plasticity Preservation for Deep Reinforcement Learning in Adaptive Video Streaming](https://mlsanity.com/paper/2505.01584/) (2025)
- [CEPAE: Conditional Entropy-Penalized Autoencoders for Time Series Counterfactuals](https://mlsanity.com/paper/2602.15546/) (2026)
- [Teleporter Theory: A General and Simple Approach for Modeling Cross-World Counterfactual Causality](https://mlsanity.com/paper/2406.11501/) (2024)
- [From Simulation to Deep Learning: Survey on Network Performance Modeling Approaches](https://mlsanity.com/paper/2603.28394/) (2026)
- [NeuralEmu: in situ Measurement-Driven, ML-based, High-Fidelity 5G Network Emulation](https://mlsanity.com/paper/2604.26080/) (2026)

## Abstract (arXiv)

We present CausalSim, a causal framework for unbiased trace-driven simulation. Current trace-driven simulators assume that the interventions being simulated (e.g., a new algorithm) would not affect the validity of the traces. However, real-world traces are often biased by the choices algorithms make during trace collection, and hence replaying traces under an intervention may lead to incorrect results. CausalSim addresses this challenge by learning a causal model of the system dynamics and latent factors capturing the underlying system conditions during trace collection. It learns these models using an initial randomized control trial (RCT) under a fixed set of algorithms, and then applies them to remove biases from trace data when simulating new algorithms. Key to CausalSim is mapping unbiased trace-driven simulation to a tensor completion problem with extremely sparse observations. By exploiting a basic distributional invariance property present in RCT data, CausalSim enables a novel tensor completion method despite the sparsity of observations. Our extensive evaluation of CausalSim on both real and synthetic datasets, including more than ten months of real data from the Puffer video streaming system shows it improves simulation accuracy, reducing errors by 53% and 61% on average compared to expert-designed and supervised learning baselines. Moreover, CausalSim provides markedly different insights about ABR algorithms compared to the biased baseline simulator, which we validate with a real deployment.