Tools
Sorted by:
Try your query at:
 |
 |
 |
 |
 |
 |
Results 1 - 10
of
124
Learning rotations with little regret
- In COLT
, 2010
"... We describe online algorithms for learning a rotation from pairs of unit vectors in R n. We show that the expected regret of our online algorithm compared to the best fixed rotation chosen offline is O ( √ nL), where L is the loss of the best rotation. We also give a lower bound that proves that th ..."
Abstract
-
Cited by 9 (5 self)
- Add to MetaCart
We describe online algorithms for learning a rotation from pairs of unit vectors in R n. We show that the expected regret of our online algorithm compared to the best fixed rotation chosen offline is O ( √ nL), where L is the loss of the best rotation. We also give a lower bound that proves
Corrigendum to "Learning rotations with little regret" . . .
, 2010
"... There is an unfortunate error in our paper “Learning rotations with little regret” [HKW10] which appeared in COLT 2010. The sampling procedure for the noise matrix given in [HKW10] does not produce matrices with the right density. In this corrigendum, we describe the error, and give a correct sampli ..."
Abstract
-
Cited by 1 (1 self)
- Add to MetaCart
There is an unfortunate error in our paper “Learning rotations with little regret” [HKW10] which appeared in COLT 2010. The sampling procedure for the noise matrix given in [HKW10] does not produce matrices with the right density. In this corrigendum, we describe the error, and give a correct
Skill Transferability, Regret and Mobility ∗
, 2003
"... After graduation many students start working in sectors not related to their field of study and participate in training targeted at work in other sectors. In this paper we look at job mobility immediately after graduation from the perspective that educational choices have been made when these pupils ..."
Abstract
- Add to MetaCart
these pupils had little experience with the actual working life in these professions. We develop a model in which students accumulate partially transferable human capital but also learn about their professional preferences at university and during the first years in the labor market. As a consequence, after
Big Learning with Little RAM
"... In large-scale machine learning, available memory (RAM) is often a key constraint, both during model training and when making new predictions. In this paper, we reduce memory cost by projecting our weight vector β ∈ R d onto a coarse discrete set using randomized rounding. Because the values of the ..."
Abstract
- Add to MetaCart
In large-scale machine learning, available memory (RAM) is often a key constraint, both during model training and when making new predictions. In this paper, we reduce memory cost by projecting our weight vector β ∈ R d onto a coarse discrete set using randomized rounding. Because the values
Global Nash convergence of Foster and Young’s regret testing
- Games and Economic Behavior
, 2007
"... We construct an uncoupled randomized strategy of repeated play such that, if every player follows such a strategy, then the joint mixed strategy profiles converge, almost surely, to a Nash equilibrium of the one-shot game. The procedure requires very little in terms of players’ information about the ..."
Abstract
-
Cited by 33 (0 self)
- Add to MetaCart
We construct an uncoupled randomized strategy of repeated play such that, if every player follows such a strategy, then the joint mixed strategy profiles converge, almost surely, to a Nash equilibrium of the one-shot game. The procedure requires very little in terms of players’ information about
Learning rotations online
, 2010
"... In this paper we show that the matrix von Mises-Fisher (vMF) distribution is a reasonable distribution upon which to build an online density estimation scheme for rotation matrices. We also consider a special case, the unit circle, for initial experimentation. The vector and matrix vMF distributions ..."
Abstract
-
Cited by 1 (1 self)
- Add to MetaCart
In this paper we show that the matrix von Mises-Fisher (vMF) distribution is a reasonable distribution upon which to build an online density estimation scheme for rotation matrices. We also consider a special case, the unit circle, for initial experimentation. The vector and matrix v
Regression without Regrets: A modular approach to linear models in (quasi)-experiments.
, 2013
"... The design of a randomized study guarantees not only clear and “in-terpretable comparisons”(Kinder and Palfrey, 1993, page 7) but valid statistical tests even in the absence of large samples or known data generating processes for outcomes (Fisher, 1935, Chap 2). Yet, while design alone yields valid ..."
Abstract
- Add to MetaCart
tests the tests could lack power: a valid but wide confidence interval may be more useful than a misleadingly narrow confidence interval, but still shed little light on the theory motivating the study. After a brief demonstration of Fisher’s statistical framework (to fix ideas about the validity
Skill Transferability, Regret and Mobility ROA-RM-2006/2E
, 2006
"... After graduation many students start working in sectors not related to their field of study or participate in training targeted at work in other sectors. In this paper, we look at mobility immediately after graduation from the perspective that educational choices have been made when these pupils had ..."
Abstract
- Add to MetaCart
had little experience of the actual working life in these professions. We develop a model where students accumulate partially transferable human capital but also learn about their professional preferences at the university and during the first years in the labor market. As a consequence of this newly
Generalization of Stochastic Visuomotor Rotations
, 2012
"... Generalization studies examine the influence of perturbations imposed on one movement onto other movements. The strength of generalization is traditionally interpreted as a reflection of the similarity of the underlying neural representations. Uncertainty fundamentally affects both sensory integrati ..."
Abstract
-
Cited by 1 (1 self)
- Add to MetaCart
integration and learning and is at the heart of many theories of neural representation. However, little is known about how uncertainty, resulting from variability in the environment, affects generalization curves. Here we extend standard movement generalization experiments to ask how uncertainty affects
Rotational object discrimination by pigeons
- J Exp Psychol-Anim Behav Process. 2009; 35: 250–265. doi: 10.1037/a0013874 PMID: 19364233
"... Four experiments examined the discrimination of directional object motion by pigeons. Four pigeons were tested in a go/no-go procedure with video stimuli of geons rotating right or left around their central y-axis. This directional discrimination was learned in 7 to 12 sessions and was not affected ..."
Abstract
-
Cited by 1 (0 self)
- Add to MetaCart
Four experiments examined the discrimination of directional object motion by pigeons. Four pigeons were tested in a go/no-go procedure with video stimuli of geons rotating right or left around their central y-axis. This directional discrimination was learned in 7 to 12 sessions
Results 1 - 10
of
124
