hunch_net hunch_net-2012 hunch_net-2012-456 knowledge-graph by maker-knowledge-mining
Source: html
Introduction: The ICML paper deadline has passed. Joelle and I were surprised to see the number of submissions jump from last year by about 50% to around 900 submissions. A tiny portion of these are immediate rejects(*), so this is a much larger set of papers than expected. The number of workshop submissions also doubled compared to last year, so ICML may grow significantly this year, if we can manage to handle the load well. The prospect of making 900 good decisions is fundamentally daunting, and success will rely heavily on the program committee and area chairs at this point. For those who want to rubberneck a bit more, here’s a breakdown of submissions by primary topic of submitted papers: 66 Reinforcement Learning 52 Supervised Learning 51 Clustering 46 Kernel Methods 40 Optimization Algorithms 39 Feature Selection and Dimensionality Reduction 33 Learning Theory 33 Graphical Models 33 Applications 29 Probabilistic Models 29 NN & Deep Learning 26 Transfer and Multi-Ta
sentIndex sentText sentNum sentScore
1 Joelle and I were surprised to see the number of submissions jump from last year by about 50% to around 900 submissions. [sent-2, score-0.417]
2 A tiny portion of these are immediate rejects(*), so this is a much larger set of papers than expected. [sent-3, score-0.168]
3 The number of workshop submissions also doubled compared to last year, so ICML may grow significantly this year, if we can manage to handle the load well. [sent-4, score-0.341]
4 The prospect of making 900 good decisions is fundamentally daunting, and success will rely heavily on the program committee and area chairs at this point. [sent-5, score-0.099]
5 But, they have to be real deadlines to achieve this, which leads us to reject late submissions & format failures to keep the deadline real for future ICMLs. [sent-7, score-0.556]
wordName wordTfidf (topN-words)
[('mining', 0.247), ('submissions', 0.242), ('methods', 0.231), ('models', 0.202), ('inductive', 0.183), ('relational', 0.183), ('deadlines', 0.137), ('inference', 0.131), ('game', 0.123), ('statistical', 0.115), ('learning', 0.106), ('topic', 0.101), ('deadline', 0.101), ('pomdps', 0.099), ('querying', 0.099), ('daunting', 0.099), ('magical', 0.099), ('doubled', 0.099), ('uncomfortably', 0.099), ('causal', 0.099), ('prospect', 0.099), ('nn', 0.099), ('outlier', 0.099), ('tiny', 0.092), ('geometric', 0.092), ('bioinformatics', 0.092), ('detection', 0.092), ('cooperative', 0.092), ('anonymity', 0.092), ('year', 0.089), ('pattern', 0.086), ('jump', 0.086), ('evolutionary', 0.086), ('retrieval', 0.086), ('carlo', 0.086), ('monte', 0.086), ('factorization', 0.086), ('breakdown', 0.086), ('rejects', 0.082), ('sparsity', 0.082), ('insights', 0.082), ('manifold', 0.082), ('security', 0.082), ('recommender', 0.079), ('compressed', 0.079), ('sensing', 0.079), ('analysis', 0.077), ('methodology', 0.076), ('failures', 0.076), ('portion', 0.076)]
simIndex simValue blogId blogTitle
same-blog 1 1.0 456 hunch net-2012-02-24-ICML+50%
Introduction: The ICML paper deadline has passed. Joelle and I were surprised to see the number of submissions jump from last year by about 50% to around 900 submissions. A tiny portion of these are immediate rejects(*), so this is a much larger set of papers than expected. The number of workshop submissions also doubled compared to last year, so ICML may grow significantly this year, if we can manage to handle the load well. The prospect of making 900 good decisions is fundamentally daunting, and success will rely heavily on the program committee and area chairs at this point. For those who want to rubberneck a bit more, here’s a breakdown of submissions by primary topic of submitted papers: 66 Reinforcement Learning 52 Supervised Learning 51 Clustering 46 Kernel Methods 40 Optimization Algorithms 39 Feature Selection and Dimensionality Reduction 33 Learning Theory 33 Graphical Models 33 Applications 29 Probabilistic Models 29 NN & Deep Learning 26 Transfer and Multi-Ta
2 0.28223583 466 hunch net-2012-06-05-ICML acceptance statistics
Introduction: People are naturally interested in slicing the ICML acceptance statistics in various ways. Here’s a rundown for the top categories. 18/66 = 0.27 in (0.18,0.36) Reinforcement Learning 10/52 = 0.19 in (0.17,0.37) Supervised Learning 9/51 = 0.18 not in (0.18, 0.37) Clustering 12/46 = 0.26 in (0.17, 0.37) Kernel Methods 11/40 = 0.28 in (0.15, 0.4) Optimization Algorithms 8/33 = 0.24 in (0.15, 0.39) Learning Theory 14/33 = 0.42 not in (0.15, 0.39) Graphical Models 10/32 = 0.31 in (0.15, 0.41) Applications (+5 invited) 8/29 = 0.28 in (0.14, 0.41]) Probabilistic Models 13/29 = 0.45 not in (0.14, 0.41) NN & Deep Learning 8/26 = 0.31 in (0.12, 0.42) Transfer and Multi-Task Learning 13/25 = 0.52 not in (0.12, 0.44) Online Learning 5/25 = 0.20 in (0.12, 0.44) Active Learning 6/22 = 0.27 in (0.14, 0.41) Semi-Superv
3 0.12576805 433 hunch net-2011-04-23-ICML workshops due
Introduction: Lihong points out that ICML workshop submissions are due April 29.
4 0.12117239 272 hunch net-2007-11-14-BellKor wins Netflix
Introduction: … but only the little prize. The BellKor team focused on integrating predictions from many different methods. The base methods consist of: Nearest Neighbor Methods Matrix Factorization Methods (asymmetric and symmetric) Linear Regression on various feature spaces Restricted Boltzman Machines The final predictor was an ensemble (as was reasonable to expect), although it’s a little bit more complicated than just a weighted average—it’s essentially a customized learning algorithm. Base approaches (1)-(3) seem like relatively well-known approaches (although I haven’t seen the asymmetric factorization variant before). RBMs are the new approach. The writeup is pretty clear for more details. The contestants are close to reaching the big prize, but the last 1.5% is probably at least as hard as what’s been done. A few new structurally different methods for making predictions may need to be discovered and added into the mixture. In other words, research may be require
5 0.10643776 438 hunch net-2011-07-11-Interesting Neural Network Papers at ICML 2011
Introduction: Maybe it’s too early to call, but with four separate Neural Network sessions at this year’s ICML , it looks like Neural Networks are making a comeback. Here are my highlights of these sessions. In general, my feeling is that these papers both demystify deep learning and show its broader applicability. The first observation I made is that the once disreputable “Neural” nomenclature is being used again in lieu of “deep learning”. Maybe it’s because Adam Coates et al. showed that single layer networks can work surprisingly well. An Analysis of Single-Layer Networks in Unsupervised Feature Learning , Adam Coates , Honglak Lee , Andrew Y. Ng (AISTATS 2011) The Importance of Encoding Versus Training with Sparse Coding and Vector Quantization , Adam Coates , Andrew Y. Ng (ICML 2011) Another surprising result out of Andrew Ng’s group comes from Andrew Saxe et al. who show that certain convolutional pooling architectures can obtain close to state-of-the-art pe
6 0.10478628 304 hunch net-2008-06-27-Reviewing Horror Stories
7 0.10335962 21 hunch net-2005-02-17-Learning Research Programs
8 0.097885437 406 hunch net-2010-08-22-KDD 2010
9 0.097733766 189 hunch net-2006-07-05-more icml papers
10 0.097428173 201 hunch net-2006-08-07-The Call of the Deep
11 0.095995471 235 hunch net-2007-03-03-All Models of Learning have Flaws
12 0.094002821 131 hunch net-2005-11-16-The Everything Ensemble Edge
13 0.092009515 452 hunch net-2012-01-04-Why ICML? and the summer conferences
14 0.091530301 2 hunch net-2005-01-24-Holy grails of machine learning?
15 0.090189219 99 hunch net-2005-08-01-Peekaboom
16 0.090143025 347 hunch net-2009-03-26-Machine Learning is too easy
17 0.089879625 453 hunch net-2012-01-28-Why COLT?
18 0.089294046 103 hunch net-2005-08-18-SVM Adaptability
19 0.089029916 454 hunch net-2012-01-30-ICML Posters and Scope
20 0.088139236 3 hunch net-2005-01-24-The Humanloop Spectrum of Machine Learning
topicId topicWeight
[(0, 0.217), (1, -0.028), (2, -0.019), (3, -0.074), (4, 0.143), (5, 0.011), (6, -0.048), (7, 0.017), (8, 0.038), (9, -0.146), (10, -0.001), (11, -0.035), (12, -0.115), (13, -0.052), (14, -0.046), (15, 0.074), (16, 0.01), (17, 0.003), (18, -0.045), (19, -0.074), (20, 0.003), (21, -0.141), (22, -0.01), (23, 0.021), (24, -0.043), (25, -0.029), (26, 0.006), (27, -0.049), (28, -0.016), (29, -0.008), (30, 0.085), (31, -0.077), (32, 0.039), (33, -0.065), (34, -0.054), (35, 0.124), (36, 0.056), (37, -0.058), (38, -0.0), (39, -0.006), (40, -0.012), (41, 0.027), (42, -0.024), (43, -0.002), (44, -0.15), (45, 0.063), (46, -0.078), (47, 0.033), (48, 0.035), (49, 0.089)]
simIndex simValue blogId blogTitle
same-blog 1 0.93437994 456 hunch net-2012-02-24-ICML+50%
Introduction: The ICML paper deadline has passed. Joelle and I were surprised to see the number of submissions jump from last year by about 50% to around 900 submissions. A tiny portion of these are immediate rejects(*), so this is a much larger set of papers than expected. The number of workshop submissions also doubled compared to last year, so ICML may grow significantly this year, if we can manage to handle the load well. The prospect of making 900 good decisions is fundamentally daunting, and success will rely heavily on the program committee and area chairs at this point. For those who want to rubberneck a bit more, here’s a breakdown of submissions by primary topic of submitted papers: 66 Reinforcement Learning 52 Supervised Learning 51 Clustering 46 Kernel Methods 40 Optimization Algorithms 39 Feature Selection and Dimensionality Reduction 33 Learning Theory 33 Graphical Models 33 Applications 29 Probabilistic Models 29 NN & Deep Learning 26 Transfer and Multi-Ta
2 0.75743747 466 hunch net-2012-06-05-ICML acceptance statistics
Introduction: People are naturally interested in slicing the ICML acceptance statistics in various ways. Here’s a rundown for the top categories. 18/66 = 0.27 in (0.18,0.36) Reinforcement Learning 10/52 = 0.19 in (0.17,0.37) Supervised Learning 9/51 = 0.18 not in (0.18, 0.37) Clustering 12/46 = 0.26 in (0.17, 0.37) Kernel Methods 11/40 = 0.28 in (0.15, 0.4) Optimization Algorithms 8/33 = 0.24 in (0.15, 0.39) Learning Theory 14/33 = 0.42 not in (0.15, 0.39) Graphical Models 10/32 = 0.31 in (0.15, 0.41) Applications (+5 invited) 8/29 = 0.28 in (0.14, 0.41]) Probabilistic Models 13/29 = 0.45 not in (0.14, 0.41) NN & Deep Learning 8/26 = 0.31 in (0.12, 0.42) Transfer and Multi-Task Learning 13/25 = 0.52 not in (0.12, 0.44) Online Learning 5/25 = 0.20 in (0.12, 0.44) Active Learning 6/22 = 0.27 in (0.14, 0.41) Semi-Superv
3 0.63215262 272 hunch net-2007-11-14-BellKor wins Netflix
Introduction: … but only the little prize. The BellKor team focused on integrating predictions from many different methods. The base methods consist of: Nearest Neighbor Methods Matrix Factorization Methods (asymmetric and symmetric) Linear Regression on various feature spaces Restricted Boltzman Machines The final predictor was an ensemble (as was reasonable to expect), although it’s a little bit more complicated than just a weighted average—it’s essentially a customized learning algorithm. Base approaches (1)-(3) seem like relatively well-known approaches (although I haven’t seen the asymmetric factorization variant before). RBMs are the new approach. The writeup is pretty clear for more details. The contestants are close to reaching the big prize, but the last 1.5% is probably at least as hard as what’s been done. A few new structurally different methods for making predictions may need to be discovered and added into the mixture. In other words, research may be require
4 0.55651271 321 hunch net-2008-10-19-NIPS 2008 workshop on Kernel Learning
Introduction: We’d like to invite hunch.net readers to participate in the NIPS 2008 workshop on kernel learning. While the main focus is on automatically learning kernels from data, we are also also looking at the broader questions of feature selection, multi-task learning and multi-view learning. There are no restrictions on the learning problem being addressed (regression, classification, etc), and both theoretical and applied work will be considered. The deadline for submissions is October 24 . More detail can be found here . Corinna Cortes, Arthur Gretton, Gert Lanckriet, Mehryar Mohri, Afshin Rostamizadeh
5 0.53244239 438 hunch net-2011-07-11-Interesting Neural Network Papers at ICML 2011
Introduction: Maybe it’s too early to call, but with four separate Neural Network sessions at this year’s ICML , it looks like Neural Networks are making a comeback. Here are my highlights of these sessions. In general, my feeling is that these papers both demystify deep learning and show its broader applicability. The first observation I made is that the once disreputable “Neural” nomenclature is being used again in lieu of “deep learning”. Maybe it’s because Adam Coates et al. showed that single layer networks can work surprisingly well. An Analysis of Single-Layer Networks in Unsupervised Feature Learning , Adam Coates , Honglak Lee , Andrew Y. Ng (AISTATS 2011) The Importance of Encoding Versus Training with Sparse Coding and Vector Quantization , Adam Coates , Andrew Y. Ng (ICML 2011) Another surprising result out of Andrew Ng’s group comes from Andrew Saxe et al. who show that certain convolutional pooling architectures can obtain close to state-of-the-art pe
6 0.53226042 3 hunch net-2005-01-24-The Humanloop Spectrum of Machine Learning
7 0.51473504 224 hunch net-2006-12-12-Interesting Papers at NIPS 2006
8 0.50807446 444 hunch net-2011-09-07-KDD and MUCMD 2011
9 0.48564637 403 hunch net-2010-07-18-ICML & COLT 2010
10 0.48361403 139 hunch net-2005-12-11-More NIPS Papers
11 0.48007676 337 hunch net-2009-01-21-Nearly all natural problems require nonlinearity
12 0.47193331 319 hunch net-2008-10-01-NIPS 2008 workshop on ‘Learning over Empirical Hypothesis Spaces’
13 0.46345252 140 hunch net-2005-12-14-More NIPS Papers II
14 0.46247634 325 hunch net-2008-11-10-ICML Reviewing Criteria
15 0.46128798 189 hunch net-2006-07-05-more icml papers
16 0.45963246 329 hunch net-2008-11-28-A Bumper Crop of Machine Learning Graduates
17 0.45931166 144 hunch net-2005-12-28-Yet more nips thoughts
18 0.44979331 2 hunch net-2005-01-24-Holy grails of machine learning?
19 0.44668064 21 hunch net-2005-02-17-Learning Research Programs
20 0.4390381 280 hunch net-2007-12-20-Cool and Interesting things at NIPS, take three
topicId topicWeight
[(27, 0.146), (30, 0.018), (38, 0.046), (48, 0.038), (49, 0.023), (53, 0.079), (55, 0.078), (77, 0.02), (92, 0.018), (94, 0.018), (95, 0.441)]
simIndex simValue blogId blogTitle
1 0.97105265 390 hunch net-2010-03-12-Netflix Challenge 2 Canceled
Introduction: The second Netflix prize is canceled due to privacy problems . I continue to believe my original assessment of this paper, that the privacy break was somewhat overstated. I still haven’t seen any serious privacy failures on the scale of the AOL search log release . I expect privacy concerns to continue to be a big issue when dealing with data releases by companies or governments. The theory of maintaining privacy while using data is improving, but it is not yet in a state where the limits of what’s possible are clear let alone how to achieve these limits in a manner friendly to a prediction competition.
2 0.96606839 479 hunch net-2013-01-31-Remote large scale learning class participation
Introduction: Yann and I have arranged so that people who are interested in our large scale machine learning class and not able to attend in person can follow along via two methods. Videos will be posted with about a 1 day delay on techtalks . This is a side-by-side capture of video+slides from Weyond . We are experimenting with Piazza as a discussion forum. Anyone is welcome to subscribe to Piazza and ask questions there, where I will be monitoring things. update2 : Sign up here . The first lecture is up now, including the revised version of the slides which fixes a few typos and rounds out references.
3 0.96361572 30 hunch net-2005-02-25-Why Papers?
Introduction: Makc asked a good question in comments—”Why bother to make a paper, at all?” There are several reasons for writing papers which may not be immediately obvious to people not in academia. The basic idea is that papers have considerably more utility than the obvious “present an idea”. Papers are a formalized units of work. Academics (especially young ones) are often judged on the number of papers they produce. Papers have a formalized method of citing and crediting other—the bibliography. Academics (especially older ones) are often judged on the number of citations they receive. Papers enable a “more fair” anonymous review. Conferences receive many papers, from which a subset are selected. Discussion forums are inherently not anonymous for anyone who wants to build a reputation for good work. Papers are an excuse to meet your friends. Papers are the content of conferences, but much of what you do is talk to friends about interesting problems while there. Sometimes yo
4 0.95905948 319 hunch net-2008-10-01-NIPS 2008 workshop on ‘Learning over Empirical Hypothesis Spaces’
Introduction: This workshop asks for insights how far we may/can push the theoretical boundary of using data in the design of learning machines. Can we express our classification rule in terms of the sample, or do we have to stick to a core assumption of classical statistical learning theory, namely that the hypothesis space is to be defined independent from the sample? This workshop is particularly interested in – but not restricted to – the ‘luckiness framework’ and the recently introduced notion of ‘compatibility functions’ in a semi-supervised learning context (more information can be found at http://www.kuleuven.be/wehys ).
5 0.94544375 389 hunch net-2010-02-26-Yahoo! ML events
Introduction: Yahoo! is sponsoring two machine learning events that might interest people. The Key Scientific Challenges program (due March 5) for Machine Learning and Statistics offers $5K (plus bonuses) for graduate students working on a core problem of interest to Y! If you are already working on one of these problems, there is no reason not to submit, and if you aren’t you might want to think about it for next year, as I am confident they all press the boundary of the possible in Machine Learning. There are 7 days left. The Learning to Rank challenge (due May 31) offers an $8K first prize for the best ranking algorithm on a real (and really used) dataset for search ranking, with presentations at an ICML workshop. Unlike the Netflix competition, there are prizes for 2nd, 3rd, and 4th place, perhaps avoiding the heartbreak the ensemble encountered. If you think you know how to rank, you should give it a try, and we might all learn something. There are 3 months left.
same-blog 6 0.9406476 456 hunch net-2012-02-24-ICML+50%
7 0.89680433 127 hunch net-2005-11-02-Progress in Active Learning
8 0.86254179 344 hunch net-2009-02-22-Effective Research Funding
9 0.83149028 373 hunch net-2009-10-03-Static vs. Dynamic multiclass prediction
10 0.77052265 462 hunch net-2012-04-20-Both new: STOC workshops and NEML
11 0.75696826 234 hunch net-2007-02-22-Create Your Own ICML Workshop
12 0.75409335 105 hunch net-2005-08-23-(Dis)similarities between academia and open source programmers
13 0.63329136 445 hunch net-2011-09-28-Somebody’s Eating Your Lunch
14 0.63083637 7 hunch net-2005-01-31-Watchword: Assumption
15 0.62112153 466 hunch net-2012-06-05-ICML acceptance statistics
16 0.61934054 464 hunch net-2012-05-03-Microsoft Research, New York City
17 0.60918981 478 hunch net-2013-01-07-NYU Large Scale Machine Learning Class
18 0.6081568 455 hunch net-2012-02-20-Berkeley Streaming Data Workshop
19 0.60148036 36 hunch net-2005-03-05-Funding Research
20 0.59157026 275 hunch net-2007-11-29-The Netflix Crack