Non-asymptotic calibration and resolution
Vladimir Vovk
Abstract
We analyze a new algorithm for probability forecasting of binary observations on the basis of the available data, without making any assumptions about the way the observations are generated. The algorithm is shown to be well calibrated and to have good resolution for long enough sequences of observations and for a suitable choice of its parameter, a kernel on the Cartesian product of the forecast space [0,1] and the data space. Our main results are non-asymptotic: we establish explicit inequalities, shown to be tight, for the performance of the algorithm.
Create a lesson
Related papers
TopGQ: Fast GNN Post-Training Quantization Leveraging Topology Information
Dain Kwon, Kanghyun Choi, Hyeyoon Lee et al.
Foundation Models Meet Agriculture: Challenges Beyond Pretraining
Vishal Nedungadi, Xingguo Xiong, Marc Rußwurm et al.
Uncertainty of Vision Medical Foundation Models
Haoxu Huang, Narges Razavian
DASC: Decay-Aware State Compression for Hybrid Linear-Attention Serving
Yanqi Yu, Pingwei Sun, Jianchao Tan et al.
RSLM: Training-Free Vector Quantization for Approximate Nearest Neighbor Search
Rastislav Lenhardt, Teodora Dobos, Thomas Vecchiato et al.
Convergence rates for the RMSprop optimizer with full control of the hyperparameters
Steffen Dereich, Arnulf Jentzen