Date/heure
Date(s) - 22/11/2012
14 h 00 min - 15 h 00 min

Catégories Pas de Catégories

$$

Date/heure
Date(s) - 22/11/2012
14 h 00 min - 15 h 00 min

Catégories Pas de Catégories

$Online\; confusion\; learning\; and\; passive-aggressive\; scheme\; By\; Liva\; Ralaivola,\; LIF.\; This\; work\; provides\; the\; first\; —\; to\; the\; best\; of\; our\; knowledge\; —\; analysis\; of\; online\; learning\; algorithms\; for\; multiclass\; problems\; when\; the\; confusion\; matrix\; is\; taken\; as\; a\; performance\; measure.\; The\; work\; builds\; upon\; recent\; and\; elegant\; results\; on\; non-\; commutative\; concentration\; inequalities,\; i.e.\; concentration\; inequalities\; that\; apply\; to\; matrices,\; and\; more\; precisely\; to\; matrix\; martingales.\; We\; do\; establish\; generalization\; bounds\; for\; online\; learning\; algorithms\; and\; show\; how\; the\; theoretical\; study\; motivates\; the\; proposition\; of\; a\; new\; confusion-friendly\; learning\; procedure.\; This\; learning\; algorithm,\; called\; COPA\; (for\; COnfusion\; Passive-Aggressive)\; is\; a\; passive-\; aggressive\; learning\; algorithm;\; it\; is\; shown\; that\; the\; update\; equations\; for\; COPA\; can\; be\; computed\; analytically,\; thus\; allowing\; the\; user\; from\; not\; having\; to\; recourse\; to\; any\; optimization\; package\; to\; implement\; it.$

Date/heure
Date(s) - 22/11/2012
14 h 00 min - 15 h 00 min

Catégories Pas de Catégories

$Online\; confusion\; learning\; and\; passive-aggressive\; scheme\backslash nBy\; Liva\; Ralaivola,\; LIF.\backslash nThis\; work\; provides\; the\; first\; —\; to\; the\; best\; of\; our\; knowledge\; —\; analysis\; of\; online\; learning\; algorithms\; for\; multiclass\; problems\; when\; the\; confusion\; matrix\; is\; taken\; as\; a\; performance\; measure.\; The\; work\; builds\; upon\; recent\; and\; elegant\; results\; on\; non-\; commutative\; concentration\; inequalities,\; i.e.\; concentration\; inequalities\; that\; apply\; to\; matrices,\; and\; more\; precisely\; to\; matrix\; martingales.\; We\; do\; establish\; generalization\; bounds\; for\; online\; learning\; algorithms\; and\; show\; how\; the\; theoretical\; study\; motivates\; the\; proposition\; of\; a\; new\; confusion-friendly\; learning\; procedure.\; This\; learning\; algorithm,\; called\; COPA\; (for\; COnfusion\; Passive-Aggressive)\; is\; a\; passive-\; aggressive\; learning\; algorithm\backslash \; ;\; it\; is\; shown\; that\; the\; update\; equations\; for\; COPA\; can\; be\; computed\; analytically,\; thus\; allowing\; the\; user\; from\; not\; having\; to\; recourse\; to\; any\; optimization\; package\; to\; implement\; it.[$