Author manuscript, published in "ACM-GECCO Genetic and Evolutionary Computation Conference (2009)" Benchmarking a BI-Population CMA-ES on the BBOB-2009 Function Testbed

2009

Citations in the corpus

• SGDR: Stochastic Gradient Descent with Warm Restarts (2016, background): “This approach works best on multimodal functions with a global funnel structure and also improves the results on ill-conditioned problems where numerical issues might lead to premature convergence when λ is small (Hansen, 2009).”
• Bio-inspired computation: Where we stand and what's next (2019, unknown): “different sizes are simultaneously used [307].”
• Natural Evolution Strategies (2008, methodology): “One simple yet important variant, inspired by Ros and Hansen (2008), is to use separable search distributions to improve the update complexity from cubic or quadratic to linear.”
• SGDR: Stochastic Gradient Descent with Restarts (2016, background): “This approach works best on multimodal functions with a global funnel structure and also improves the results on ill-conditioned problems where numerical issues might lead to premature convergence when λ is small (Hansen, 2009).”
• Improving the search performance of SHADE using linear population size reduction (2014, methodology): “NBIPOPACMA-ES [19], which is improved variants of BIPOP-CMAES [30], adaptively allocates resources among the two components (IPOP-CMA-ES and multistart CMA-ES).”
• Parameter Control in Evolutionary Algorithms: Trends and Challenges (2015, unknown): “6 A further extension is suggested with the BIPOP-CMA-ES by Hansen [97], [96].”
• Alternative Restart Strategies for CMA-ES (2012, methodology): “The default parameters of CMA-ES [11, 5] are used.”
• Black-box data-efficient policy search for robotics (2017, methodology): “In this work, we use BIPOP-CMA-ES with restarts [37], which is one of best CMA-ES variants on benchmarks with both noiseless and noisy functions [37], [38].”