Statistical learning theory 2018 2019 - История изменений

Mednik: Откат правок Seosky (обсуждение) к версии Bbauwens

2022-08-26T06:36:26Z

Откат правок Seosky (обсуждение) к версии Bbauwens

Внесённые изменения

Seosky в 23:27, 17 августа 2022

2022-08-17T23:27:37Z

Внесённые изменения

Bbauwens в 16:12, 12 декабря 2018

2018-12-12T16:12:50Z

← Предыдущая версия		Версия от 16:12, 12 декабря 2018
Строка 46:		Строка 46:
	\| 12 Nov \|\| Deep boosting, we study the paper [http://www.cs.nyu.edu/~mohri/pub/mboost.pdf Multi-class deep boosting], V. Kuznetsov, M Mohri, and U. Syed, Advances in Neural Information Processing Systems, p2501--2509, 2014. Notes will be provided. \|\| [https://www.dropbox.com/s/tc7drmxwu53opzq/09lect.pdf?dl=0 lecture9.pdf] \|\| [https://www.dropbox.com/s/lsu6tgmc767u3yd/09sem.pdf?dl=0 Problem list 9] \|\| [https://www.dropbox.com/s/8wmswbynzx0s9hd/09sol.pdf?dl=0 Solutions 9.]		\| 12 Nov \|\| Deep boosting, we study the paper [http://www.cs.nyu.edu/~mohri/pub/mboost.pdf Multi-class deep boosting], V. Kuznetsov, M Mohri, and U. Syed, Advances in Neural Information Processing Systems, p2501--2509, 2014. Notes will be provided. \|\| [https://www.dropbox.com/s/tc7drmxwu53opzq/09lect.pdf?dl=0 lecture9.pdf] \|\| [https://www.dropbox.com/s/lsu6tgmc767u3yd/09sem.pdf?dl=0 Problem list 9] \|\| [https://www.dropbox.com/s/8wmswbynzx0s9hd/09sol.pdf?dl=0 Solutions 9.]
	\|-		\|-
	\| 19 Nov \|\| Support vector machines, primal and dual optimization problem, risk bounds. \|\| See chapt. 5 of Mohri's book \|\| [https://www.dropbox.com/s/ys37nsdfz3aa4ry/10sem.pdf?dl=0 Problem list 10]\|\|		\| 19 Nov \|\| Support vector machines, primal and dual optimization problem, risk bounds. \|\| See chapt. 5 of Mohri's book \|\| [https://www.dropbox.com/s/ys37nsdfz3aa4ry/10sem.pdf?dl=0 Problem list 10]\|\| No solution.
	\|-		\|-
	\| 26 Nov \|\| Kernels, Kernel reproducing Hilbert spaces, representer theorem, examples of kernels \|\| [https://www.dropbox.com/s/xkic1j6r516ierl/11lect.pdf?dl=0 lecture11.pdf] \|\| [https://www.dropbox.com/s/g3huq5aqzdaesrg/11sem.pdf?dl=0 Problem set 11] \|\| Solutions: see lecture11.pdf		\| 26 Nov \|\| Kernels, Kernel reproducing Hilbert spaces, representer theorem, examples of kernels \|\| [https://www.dropbox.com/s/xkic1j6r516ierl/11lect.pdf?dl=0 lecture11.pdf] \|\| [https://www.dropbox.com/s/g3huq5aqzdaesrg/11sem.pdf?dl=0 Problem set 11] \|\| Solutions: see lecture11.pdf
	\|-		\|-
	\| 3 Dec \|\| A polynomial time improper learning algorithm for constant depth L1-regularized neural networks, from [http://www.jmlr.org/proceedings/papers/v48/zhangd16.pdf this paper]. Online algorithms: halving algorithm, weighted and exponentially weighted average algorithms. See Mohri's book Sections 7.1 and 7.2. \|\| [https://www.dropbox.com/s/aq6798jps111l86/12lect.pdf?dl=0 lecture12.pdf] \|\| [https://www.dropbox.com/s/o4t6smc70o1bt3t/12sem.pdf?dl=0 Problem list 12] \|\|		\| 3 Dec \|\| A polynomial time improper learning algorithm for constant depth L1-regularized neural networks, from [http://www.jmlr.org/proceedings/papers/v48/zhangd16.pdf this paper]. Online algorithms: halving algorithm, weighted and exponentially weighted average algorithms. See Mohri's book Sections 7.1 and 7.2. \|\| [https://www.dropbox.com/s/aq6798jps111l86/12lect.pdf?dl=0 lecture12.pdf] \|\| [https://www.dropbox.com/s/o4t6smc70o1bt3t/12sem.pdf?dl=0 Problem list 12] \|\| No solution.
	\|-		\|-
	\| 10 Dec \|\| We finish online learning. Discuss the algorithm from [http://papers.nips.cc/paper/4616-bandit-algorithms-boost-brain-computer-interfaces-for-motor-task-selection-of-a-brain-controlled-button.pdf this paper]. \|\| \|\| See previous list. \|\|		\| 10 Dec \|\| We finish online learning. Discuss the algorithm from [http://papers.nips.cc/paper/4616-bandit-algorithms-boost-brain-computer-interfaces-for-motor-task-selection-of-a-brain-controlled-button.pdf this paper]. \|\| \|\| See previous list. \|\|

Bbauwens в 16:00, 12 декабря 2018

2018-12-12T16:00:13Z

← Предыдущая версия		Версия от 16:00, 12 декабря 2018
Строка 44:		Строка 44:
	\| 21 Oct \|\| Margin theory and risk bounds for boosting. \|\| [https://www.dropbox.com/s/o5zae3d8nw5eexw/08lect.pdf?dl=0 lecture8.pdf] \|\| [https://www.dropbox.com/s/xg7u3ss1a0vog5j/08sem.pdf?dl=0 Problem list 8]\|\| See lecture6.pdf for ex. 8.6.		\| 21 Oct \|\| Margin theory and risk bounds for boosting. \|\| [https://www.dropbox.com/s/o5zae3d8nw5eexw/08lect.pdf?dl=0 lecture8.pdf] \|\| [https://www.dropbox.com/s/xg7u3ss1a0vog5j/08sem.pdf?dl=0 Problem list 8]\|\| See lecture6.pdf for ex. 8.6.
	\|-		\|-
	\| 12 Nov \|\| Deep boosting, we study the paper [http://www.cs.nyu.edu/~mohri/pub/mboost.pdf Multi-class deep boosting], V. Kuznetsov, M Mohri, and U. Syed, Advances in Neural Information Processing Systems, p2501--2509, 2014. Notes will be provided. \|\| \|\| [https://www.dropbox.com/s/lsu6tgmc767u3yd/09sem.pdf?dl=0 Problem list 9] \|\| [https://www.dropbox.com/s/8wmswbynzx0s9hd/09sol.pdf?dl=0 Solutions 9.]		\| 12 Nov \|\| Deep boosting, we study the paper [http://www.cs.nyu.edu/~mohri/pub/mboost.pdf Multi-class deep boosting], V. Kuznetsov, M Mohri, and U. Syed, Advances in Neural Information Processing Systems, p2501--2509, 2014. Notes will be provided. \|\| [https://www.dropbox.com/s/tc7drmxwu53opzq/09lect.pdf?dl=0 lecture9.pdf] \|\| [https://www.dropbox.com/s/lsu6tgmc767u3yd/09sem.pdf?dl=0 Problem list 9] \|\| [https://www.dropbox.com/s/8wmswbynzx0s9hd/09sol.pdf?dl=0 Solutions 9.]
	\|-		\|-
	\| 19 Nov \|\| Support vector machines, primal and dual optimization problem, risk bounds. \|\| See chapt. 5 of Mohri's book \|\| [https://www.dropbox.com/s/ys37nsdfz3aa4ry/10sem.pdf?dl=0 Problem list 10]\|\|		\| 19 Nov \|\| Support vector machines, primal and dual optimization problem, risk bounds. \|\| See chapt. 5 of Mohri's book \|\| [https://www.dropbox.com/s/ys37nsdfz3aa4ry/10sem.pdf?dl=0 Problem list 10]\|\|

Bbauwens в 15:30, 11 декабря 2018

2018-12-11T15:30:46Z

← Предыдущая версия		Версия от 15:30, 11 декабря 2018
Строка 52:		Строка 52:
	\| 3 Dec \|\| A polynomial time improper learning algorithm for constant depth L1-regularized neural networks, from [http://www.jmlr.org/proceedings/papers/v48/zhangd16.pdf this paper]. Online algorithms: halving algorithm, weighted and exponentially weighted average algorithms. See Mohri's book Sections 7.1 and 7.2. \|\| [https://www.dropbox.com/s/aq6798jps111l86/12lect.pdf?dl=0 lecture12.pdf] \|\| [https://www.dropbox.com/s/o4t6smc70o1bt3t/12sem.pdf?dl=0 Problem list 12] \|\|		\| 3 Dec \|\| A polynomial time improper learning algorithm for constant depth L1-regularized neural networks, from [http://www.jmlr.org/proceedings/papers/v48/zhangd16.pdf this paper]. Online algorithms: halving algorithm, weighted and exponentially weighted average algorithms. See Mohri's book Sections 7.1 and 7.2. \|\| [https://www.dropbox.com/s/aq6798jps111l86/12lect.pdf?dl=0 lecture12.pdf] \|\| [https://www.dropbox.com/s/o4t6smc70o1bt3t/12sem.pdf?dl=0 Problem list 12] \|\|
	\|-		\|-
	\| 10 Dec \|\| We finish online learning. Discuss the algorithm from [http://papers.nips.cc/paper/4616-bandit-algorithms-boost-brain-computer-interfaces-for-motor-task-selection-of-a-brain-controlled-button.pdf this paper]. \|\| See previous list. \|\| \|\|		\| 10 Dec \|\| We finish online learning. Discuss the algorithm from [http://papers.nips.cc/paper/4616-bandit-algorithms-boost-brain-computer-interfaces-for-motor-task-selection-of-a-brain-controlled-button.pdf this paper]. \|\| \|\| See previous list. \|\|
	\|}		\|}

Bbauwens в 15:30, 11 декабря 2018

2018-12-11T15:30:20Z

← Предыдущая версия		Версия от 15:30, 11 декабря 2018
Строка 52:		Строка 52:
	\| 3 Dec \|\| A polynomial time improper learning algorithm for constant depth L1-regularized neural networks, from [http://www.jmlr.org/proceedings/papers/v48/zhangd16.pdf this paper]. Online algorithms: halving algorithm, weighted and exponentially weighted average algorithms. See Mohri's book Sections 7.1 and 7.2. \|\| [https://www.dropbox.com/s/aq6798jps111l86/12lect.pdf?dl=0 lecture12.pdf] \|\| [https://www.dropbox.com/s/o4t6smc70o1bt3t/12sem.pdf?dl=0 Problem list 12] \|\|		\| 3 Dec \|\| A polynomial time improper learning algorithm for constant depth L1-regularized neural networks, from [http://www.jmlr.org/proceedings/papers/v48/zhangd16.pdf this paper]. Online algorithms: halving algorithm, weighted and exponentially weighted average algorithms. See Mohri's book Sections 7.1 and 7.2. \|\| [https://www.dropbox.com/s/aq6798jps111l86/12lect.pdf?dl=0 lecture12.pdf] \|\| [https://www.dropbox.com/s/o4t6smc70o1bt3t/12sem.pdf?dl=0 Problem list 12] \|\|
	\|-		\|-
	\| 10 Dec \|\| We finish online learning. Discuss the algorithm from [http://papers.nips.cc/paper/4616-bandit-algorithms-boost-brain-computer-interfaces-for-motor-task-selection-of-a-brain-controlled-button.pdf this paper]. \|\| \|\| \|\|		\| 10 Dec \|\| We finish online learning. Discuss the algorithm from [http://papers.nips.cc/paper/4616-bandit-algorithms-boost-brain-computer-interfaces-for-motor-task-selection-of-a-brain-controlled-button.pdf this paper]. \|\| See previous list. \|\| \|\|
	\|}		\|}

Bbauwens в 15:53, 9 декабря 2018

2018-12-09T15:53:43Z

← Предыдущая версия		Версия от 15:53, 9 декабря 2018
Строка 50:		Строка 50:
	\| 26 Nov \|\| Kernels, Kernel reproducing Hilbert spaces, representer theorem, examples of kernels \|\| [https://www.dropbox.com/s/xkic1j6r516ierl/11lect.pdf?dl=0 lecture11.pdf] \|\| [https://www.dropbox.com/s/g3huq5aqzdaesrg/11sem.pdf?dl=0 Problem set 11] \|\| Solutions: see lecture11.pdf		\| 26 Nov \|\| Kernels, Kernel reproducing Hilbert spaces, representer theorem, examples of kernels \|\| [https://www.dropbox.com/s/xkic1j6r516ierl/11lect.pdf?dl=0 lecture11.pdf] \|\| [https://www.dropbox.com/s/g3huq5aqzdaesrg/11sem.pdf?dl=0 Problem set 11] \|\| Solutions: see lecture11.pdf
	\|-		\|-
	\| 3 Dec \|\| A polynomial time improper learning algorithm for constant depth L1-regularized neural networks, from [http://www.jmlr.org/proceedings/papers/v48/zhangd16.pdf this paper]. Online algorithms: halving algorithm, weighted and exponentially weighted average algorithms. See Mohri's book Sections 7.1 and 7.2. \|\| \|\| [https://www.dropbox.com/s/o4t6smc70o1bt3t/12sem.pdf?dl=0 Problem list 12] \|\|		\| 3 Dec \|\| A polynomial time improper learning algorithm for constant depth L1-regularized neural networks, from [http://www.jmlr.org/proceedings/papers/v48/zhangd16.pdf this paper]. Online algorithms: halving algorithm, weighted and exponentially weighted average algorithms. See Mohri's book Sections 7.1 and 7.2. \|\| [https://www.dropbox.com/s/aq6798jps111l86/12lect.pdf?dl=0 lecture12.pdf] \|\| [https://www.dropbox.com/s/o4t6smc70o1bt3t/12sem.pdf?dl=0 Problem list 12] \|\|
	\|-		\|-
	\| 10 Dec \|\| We finish online learning. Discuss the algorithm from [http://papers.nips.cc/paper/4616-bandit-algorithms-boost-brain-computer-interfaces-for-motor-task-selection-of-a-brain-controlled-button.pdf this paper]. \|\| \|\| \|\|		\| 10 Dec \|\| We finish online learning. Discuss the algorithm from [http://papers.nips.cc/paper/4616-bandit-algorithms-boost-brain-computer-interfaces-for-motor-task-selection-of-a-brain-controlled-button.pdf this paper]. \|\| \|\| \|\|

Bbauwens в 13:04, 9 декабря 2018

2018-12-09T13:04:12Z

← Предыдущая версия		Версия от 13:04, 9 декабря 2018
Строка 50:		Строка 50:
	\| 26 Nov \|\| Kernels, Kernel reproducing Hilbert spaces, representer theorem, examples of kernels \|\| [https://www.dropbox.com/s/xkic1j6r516ierl/11lect.pdf?dl=0 lecture11.pdf] \|\| [https://www.dropbox.com/s/g3huq5aqzdaesrg/11sem.pdf?dl=0 Problem set 11] \|\| Solutions: see lecture11.pdf		\| 26 Nov \|\| Kernels, Kernel reproducing Hilbert spaces, representer theorem, examples of kernels \|\| [https://www.dropbox.com/s/xkic1j6r516ierl/11lect.pdf?dl=0 lecture11.pdf] \|\| [https://www.dropbox.com/s/g3huq5aqzdaesrg/11sem.pdf?dl=0 Problem set 11] \|\| Solutions: see lecture11.pdf
	\|-		\|-
	\| 3 Dec \|\| A polynomial time improper learning algorithm for constant depth L1-regularized neural networks, from [http://www.jmlr.org/proceedings/papers/v48/zhangd16.pdf this paper]. ~~[Notes will be written soon.]~~ Online algorithms: halving algorithm, weighted and exponentially weighted average algorithms. See Mohri's book Sections 7.1 and 7.2. \|\| \|\| [https://www.dropbox.com/s/o4t6smc70o1bt3t/12sem.pdf?dl=0 Problem list 12] \|\|		\| 3 Dec \|\| A polynomial time improper learning algorithm for constant depth L1-regularized neural networks, from [http://www.jmlr.org/proceedings/papers/v48/zhangd16.pdf this paper]. Online algorithms: halving algorithm, weighted and exponentially weighted average algorithms. See Mohri's book Sections 7.1 and 7.2. \|\| \|\| [https://www.dropbox.com/s/o4t6smc70o1bt3t/12sem.pdf?dl=0 Problem list 12] \|\|
	\|-		\|-
	\| 10 Dec \|\| We finish online learning. Discuss the algorithm from [http://papers.nips.cc/paper/4616-bandit-algorithms-boost-brain-computer-interfaces-for-motor-task-selection-of-a-brain-controlled-button.pdf this paper]. \|\| \|\| \|\|		\| 10 Dec \|\| We finish online learning. Discuss the algorithm from [http://papers.nips.cc/paper/4616-bandit-algorithms-boost-brain-computer-interfaces-for-motor-task-selection-of-a-brain-controlled-button.pdf this paper]. \|\| \|\| \|\|

Bbauwens в 13:03, 9 декабря 2018

2018-12-09T13:03:12Z

← Предыдущая версия		Версия от 13:03, 9 декабря 2018
Строка 44:		Строка 44:
	\| 21 Oct \|\| Margin theory and risk bounds for boosting. \|\| [https://www.dropbox.com/s/o5zae3d8nw5eexw/08lect.pdf?dl=0 lecture8.pdf] \|\| [https://www.dropbox.com/s/xg7u3ss1a0vog5j/08sem.pdf?dl=0 Problem list 8]\|\| See lecture6.pdf for ex. 8.6.		\| 21 Oct \|\| Margin theory and risk bounds for boosting. \|\| [https://www.dropbox.com/s/o5zae3d8nw5eexw/08lect.pdf?dl=0 lecture8.pdf] \|\| [https://www.dropbox.com/s/xg7u3ss1a0vog5j/08sem.pdf?dl=0 Problem list 8]\|\| See lecture6.pdf for ex. 8.6.
	\|-		\|-
	\| 12 Nov \|\| Deep boosting, we study the paper [http://www.cs.nyu.edu/~mohri/pub/mboost.pdf Multi-class deep boosting], V. Kuznetsov, M Mohri, and U. Syed, Advances in Neural Information Processing Systems, p2501--2509, 2014. Notes will be provided. \|\| \|\| [https://www.dropbox.com/s/lsu6tgmc767u3yd/09sem.pdf?dl=0 Problem list 9] \|\| [https://www.dropbox.com/s/8wmswbynzx0s9hd/09sol.pdf?dl=0 Solutions.]		\| 12 Nov \|\| Deep boosting, we study the paper [http://www.cs.nyu.edu/~mohri/pub/mboost.pdf Multi-class deep boosting], V. Kuznetsov, M Mohri, and U. Syed, Advances in Neural Information Processing Systems, p2501--2509, 2014. Notes will be provided. \|\| \|\| [https://www.dropbox.com/s/lsu6tgmc767u3yd/09sem.pdf?dl=0 Problem list 9] \|\| [https://www.dropbox.com/s/8wmswbynzx0s9hd/09sol.pdf?dl=0 Solutions 9.]
	\|-		\|-
	\| 19 Nov \|\| Support vector machines, primal and dual optimization problem, risk bounds. \|\| See chapt. 5 of Mohri's book \|\| [https://www.dropbox.com/s/ys37nsdfz3aa4ry/10sem.pdf?dl=0 Problem list 10]\|\|		\| 19 Nov \|\| Support vector machines, primal and dual optimization problem, risk bounds. \|\| See chapt. 5 of Mohri's book \|\| [https://www.dropbox.com/s/ys37nsdfz3aa4ry/10sem.pdf?dl=0 Problem list 10]\|\|

Bbauwens в 13:02, 9 декабря 2018

2018-12-09T13:02:30Z

← Предыдущая версия		Версия от 13:02, 9 декабря 2018
Строка 44:		Строка 44:
	\| 21 Oct \|\| Margin theory and risk bounds for boosting. \|\| [https://www.dropbox.com/s/o5zae3d8nw5eexw/08lect.pdf?dl=0 lecture8.pdf] \|\| [https://www.dropbox.com/s/xg7u3ss1a0vog5j/08sem.pdf?dl=0 Problem list 8]\|\| See lecture6.pdf for ex. 8.6.		\| 21 Oct \|\| Margin theory and risk bounds for boosting. \|\| [https://www.dropbox.com/s/o5zae3d8nw5eexw/08lect.pdf?dl=0 lecture8.pdf] \|\| [https://www.dropbox.com/s/xg7u3ss1a0vog5j/08sem.pdf?dl=0 Problem list 8]\|\| See lecture6.pdf for ex. 8.6.
	\|-		\|-
	\| 12 Nov \|\| Deep boosting, we study the paper [http://www.cs.nyu.edu/~mohri/pub/mboost.pdf Multi-class deep boosting], V. Kuznetsov, M Mohri, and U. Syed, Advances in Neural Information Processing Systems, p2501--2509, 2014. Notes will be provided. \|\| \|\| [https://www.dropbox.com/s/lsu6tgmc767u3yd/09sem.pdf?dl=0 Problem list 9] \|\|		\| 12 Nov \|\| Deep boosting, we study the paper [http://www.cs.nyu.edu/~mohri/pub/mboost.pdf Multi-class deep boosting], V. Kuznetsov, M Mohri, and U. Syed, Advances in Neural Information Processing Systems, p2501--2509, 2014. Notes will be provided. \|\| \|\| [https://www.dropbox.com/s/lsu6tgmc767u3yd/09sem.pdf?dl=0 Problem list 9] \|\| [https://www.dropbox.com/s/8wmswbynzx0s9hd/09sol.pdf?dl=0 Solutions.]
	\|-		\|-
	\| 19 Nov \|\| Support vector machines, primal and dual optimization problem, risk bounds. \|\| See chapt. 5 of Mohri's book \|\| [https://www.dropbox.com/s/ys37nsdfz3aa4ry/10sem.pdf?dl=0 Problem list 10]\|\|		\| 19 Nov \|\| Support vector machines, primal and dual optimization problem, risk bounds. \|\| See chapt. 5 of Mohri's book \|\| [https://www.dropbox.com/s/ys37nsdfz3aa4ry/10sem.pdf?dl=0 Problem list 10]\|\|