Harish G. Ramaswamy
9 papers · 2012–2024 · 6 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
π Academic Marathon Β· Half π£ Hot Topic Early Bird π Interdisciplinary Bridge Β· Bronze π Conference Polyglot Β· Silver πΊοΈ Taxonomy Completionist (22)
π
Trend Setter
ποΈ
Keyword Collector
(56)
Top co-authors
Research topics
Keywords
multi-class classification
(6)
surrogate loss
(4)
attention mechanism
(2)
loss matrix
(2)
convex surrogate
(2)
classification calibration
(2)
question answering
(1)
knowledge distillation
(1)
algorithmic fairness
(1)
probability distribution
(1)
gradient descent
(1)
multiclass learning
(1)
model interpretability
(1)
performance metric
(1)
multi-label classification
(1)
low-rank matrices
(1)
low-rank matrix
(1)
surrogate losses
(1)
image captioning
(1)
convex optimization
(1)
Papers
Consistent Multiclass Algorithms for Complex Metrics and Constraints
JMLR 2024
Inductive Bias of Gradient Descent for Weight Normalized Smooth Homogeneous Neural Nets
ALT 2022
On the Interpretability of Attention Networks
ACML 2022
On Knowledge distillation from complex networks for response prediction
NAACL 2019
On Controllable Sparse Alternatives to Softmax
NeurIPS 2018
Convex Calibration Dimension for Multiclass Loss Matrices
JMLR 2016
On the Consistency of Output Code Based Learning Algorithms for Multiclass Learning Problems
COLT 2014
Convex Calibrated Surrogates for Low-Rank Loss Matrices with Applications to Subset Ranking Losses
NeurIPS 2013
Classification Calibration Dimension for General Multiclass Losses
NeurIPS 2012