BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//pyconde-pydata-2026//speaker//PUH8YU
BEGIN:VTIMEZONE
TZID:CET
BEGIN:STANDARD
DTSTART:20001029T040000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000326T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-pyconde-pydata-2026-JPTTMK@pretalx.com
DTSTART;TZID=CET:20260414T163000
DTEND;TZID=CET:20260414T170000
DESCRIPTION:As Python developers\, we frequently tackle complex decision-ma
 king problems by writing custom scripts and heuristic algorithms. While a 
 standard greedy algorithm might provide a quick\, intuitive fix\, it rarel
 y finds the best possible solution—often leaving significant efficiency\
 , performance\, and cost-savings on the table.\n\nIn this talk\, we will e
 xplore the untapped power of mathematical optimization. We will start with
  a classic operations challenge. You will see firsthand how a standard rul
 e-based Python heuristic compares to a mathematical optimization model\, a
 nd how rigorously defining constraints and objectives can guarantee a glob
 ally optimal solution.\n\nBut optimization isn't just for traditional logi
 stics! We will also bridge the gap to Machine Learning. We will demonstrat
 e how optimization techniques can be utilized as a powerful verification s
 tep for ML models\, such as calculating the minimum pixel changes required
  to trick a neural network into a misclassification.\n\nWhile we can only 
 scratch the surface of these vast topics\, you will walk away with a fresh
  perspective on problem-solving. Whether you are automating business opera
 tions or building robust ML pipelines\, you will learn when to graduate fr
 om basic heuristics and start leveraging the "art of the optimal".
DTSTAMP:20260412T142015Z
LOCATION:Platinum [2nd Floor]
SUMMARY:The Art of the Optimal: A Pythonic Approach to Complex Decision-Mak
 ing - Justine Broihan
URL:https://pretalx.com/pyconde-pydata-2026/talk/JPTTMK/
END:VEVENT
END:VCALENDAR