Black-box optimization using neural networks
PulseAugur coverage of Black-box optimization using neural networks — every cluster mentioning Black-box optimization using neural networks across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
New methods use geometry and CNNs for algorithm selection
Two new research papers explore novel methods for selecting the best algorithm for continuous black-box optimization tasks. One paper, GeoPAS, uses geometric probing to create 2D slices of the objective landscape, encod…
-
New framework enables valid statistical inference on actively collected data
Researchers have introduced a new framework called post-ADC inference to address the challenges of statistical validity when data collected through active data collection (ADC) is reused for subsequent inferential tasks…
-
New theory analyzes guided diffusion for black-box optimization
Researchers have developed a new theoretical framework to analyze the regret behavior of guided diffusion models used in black-box optimization for structured inputs. This framework avoids common assumptions in existing…
-
New dataset BBO-Pile advances foundation models for black-box optimization
Researchers have introduced BBO-Pile, a novel open-source dataset containing over 500,000 optimization trajectories across nearly 3,100 black-boxes. This dataset aims to address the limitations of previous work, which r…