MLconf SF 2014
2014-11-14
San Francisco, United States
[MLconf SF 2014, MLconf SF 2015, MLconf SF 2016, MLconf SF 2017, MLconf SF 2019]
| title | author | length |
|---|---|---|
| Steffen Rendle, Research Scientist, Google | Steffen Rendle | 35m |
Presents a single, generic model that replaces bespoke matrix/tensor factorizations: factorization machines that take arbitrary feature vectors and learn… | ||
| Tamara Kolda, Distinguished Member of Technical Staff, Sandia National Laboratories @ MLconf SF Part | Tamara Kolda | 02m |
A focused survey of canonical polyadic (CP/PARAFAC) decompositions shows how 3D data such as time-evolving networks is written as sums of rank-one components… | ||
| Tamara Kolda, Distinguished Member of Technical Staff, Sandia National Laboratories @ MLconf SF Part | Tamara Kolda | 07m |
Describes using CP (CANDECOMP/PARAFAC) decompositions with a Poisson tensor factorization objective (KL divergence) for count data, enforcing nonnegative… | ||
| Xavier Amatriain, Director of Algorithms Engineering, Netflix | Xavier Amatriain | 29m |
Netflix runs ~50 million members, logs ~100 billion events per day and reports 7 billion hours in Q2, so engineering choices matter as much as algorithms. Ten… | ||
| Lise Getoor, Professor, Computer Science, UC Santa Cruz | Lise Getoor | 23m |
Argues that big data is intrinsically graph-structured and frames three concrete microtasks—collective classification, link prediction, and entity… | ||
| Lorien Pratt, Co-Founder & Chief Scientist, Quantellia | Lorien Pratt | 18m |
Argues that “Decision Intelligence” unifies machine learning, causal reasoning and optimization to treat each major corporate choice as an engineered artifact… | ||
| Ted Willke, Senior Principal Engineer & GM, Datacenter Group, Intel | Ted Willke | 29m |
Demo compares 1,300 molecules visually but notes the n^2 problem for millions of compounds, argues for treating graphs as a data-structure primitive by reusing… | ||
| Quoc Le, Software Engineer, Google | Quoc Le | 24m |
Proposes a practical sequence-to-sequence encoder–decoder using recurrent neural networks that encodes a variable-length sentence into a 1000-dimensional… | ||
| Arno Candel, Physicist & Hacker, 0xData | Arno Candel | 22m |
Introduces a recurrent encoder that compresses a variable-length sentence into a fixed-length vector and a recurrent decoder that generates the target one word… | ||
| Ameet Talwalkar, Assistant Professor of Computer Science, UCLA @ MLconf SF Part 1 | Ameet Talwalkar | 07m |
MLbase builds on Apache Spark and MLlib to automate model selection by searching the hyperparameter space instead of relying on ad hoc tuning. It combines new… | ||
| Ameet Talwalkar, Assistant Professor of Computer Science, UCLA @ MLconf SF Part 2 | Ameet Talwalkar | 16m |
MLlib on Spark gets an automated hyperparameter search layer called MLbase optimizer that combines batch model updates (matrix‑matrix LAPACK routines), early… | ||
| Johann Schleier Smith, Co Founder and CTO, ifwe | Johann Schleier Smith | 25m |
Company if(we) describes an event history architecture and Scala-based runtime that turns streams into live features, avoiding SQL-to-Java rewrites and… | ||
| Andy Feng, Distinguished Architect, Yahoo | Andy Feng | 27m |
Scalable Machine Learning at Yahoo
Yahoo scientists have developed variety of machine learning libraries (supervised learning, unsupervised learning, deep… | ||
| Ted Dunning, Chief Application Architect, MapR | Ted Dunning | 24m |
Describes extending co‑occurrence recommenders to near real‑time updates by pruning histories with an interaction cut and capping item frequency (frequency… | ||
| Anthony Bak, Principal Data Scientist and Mathematician, Ayasdi | Anthony Bak | 26m |
Ayasdi’s pipeline builds combinatorial summaries (Mapper-style graphs) from real-valued lens functions to reveal shape in high‑dimensional data, not just… | ||
| Scott Clark, Software Engineer, Yelp | Scott Clark | 24m |
MOE is an open source Bayesian global optimizer that models an expensive black‑box objective with a Gaussian Process, fits its kernel hyperparameters… | ||
| nothing matches | ||