πάντες ἄνθρωποι τοῦ εἰδέναι ὀρέγονται φύσει.
By nature, all human beings desire to know.
I work on state space models, signal processing, statistics, applied mathematics, and machine learning.
I write short mathematical notes about places where formal guarantees meet interpretation.
The recurring theme is that a method can be mathematically correct and still easy to read too strongly. A loss may measure one geometry while the application needs another. A guarantee may hold marginally while local behavior changes. An estimator may be biased for a good reason. A finite optimization problem may be solved exactly while the population question remains open.
Most posts use small diagnostics, examples, and geometric viewpoints to make those gaps visible.
This site contains personal and independent mathematical, statistical, and software notes. They are written outside working time, using personal resources, and are not prepared at the request of, under the supervision of, or according to the instructions of any employer or client.
The notes rely only on public mathematical literature, public software, public documentation where cited, and synthetic or schematic examples. They do not use, describe, reproduce, adapt, or disclose any employer or client work product, internal method, API, source code, dataset, benchmark, architecture, calibration procedure, validation result, business requirement, or confidential know-how.
Any connection with industrial, financial, or applied settings is purely at the level of general public mathematics, standard scientific computing, and publicly available references.