By adding a cross-covariance penalty to autoencoders, hidden factors of variation in deep networks are discovered.

Brian Cheung, Jesse A. Livezey, Arjun K. Bansal et al.

A spherical spin-glass mapping explains why SGD in large networks reaches low-energy, high-quality local minima.

Anna Choromanska, Mikael Henaff, Michael Mathieu et al.

This paper analyzes the computational complexity of training neural networks, showing over-parameterized networks are easier to optimize and proposing polynomial activation-based algorithms for depth-2 and depth-3 networks.

Roi Livni, Shai Shalev-Shwartz, Ohad Shamir

Volumetric spanners use at most 12d support points to enable low-variance exploration and efficient near-optimal BLO over general convex sets.

Elad Hazan, Zohar Karnin, Raghu Mehka

Proposes spectral and local clustering graph networks with input-size-independent parameters, effective on low-dimensional graphs.

Joan Bruna, Wojciech Zaremba, Arthur Szlam et al.

Deep Mixture of Experts excels on MNIST, learning location and class-specific experts.

David Eigen, Marc'Aurelio Ranzato, Ilya Sutskever

Four gradient estimators for stochastic binary neurons enable efficient conditional computation and sparsity in deep networks.

Yoshua Bengio, Nicholas Léonard, Aaron Courville

Introduces Exp3-DOM algorithm leveraging dominating sets to bound regret in directed, dynamic observation graphs (under 30 words)

Noga Alon, Nicolò Cesa-Bianchi, Claudio Gentile et al.

Proposes BOLD and QPM-D algorithms for online learning with delayed feedback; theoretical bounds show multiplicative regret in adversarial and additive in stochastic settings.

Pooria Joulani, András György, Csaba Szepesvári

Proposes GP-UCB-PE, combining UCB and pure exploration for parallel Gaussian process optimization, with bounds outperforming sequential methods.

Emile Contal, David Buffoni, Alexandre Robicquet et al.

Establishes Ω(T^{2/3}) regret lower bound for online learning with switching costs under bandit feedback, highlighting the difficulty compared to full-information settings.

Nicolo Cesa-Bianchi, Ofer Dekel, Ohad Shamir

Deep learning detects robotic grasps with 84% and 89% success rates.

Ian Lenz, Honglak Lee, Ashutosh Saxena

Introduces a weighted averaging scheme in projected stochastic subgradient method achieving O(1/t) convergence, with simple implementation and proof.

Simon Lacoste-Julien, Mark Schmidt, Francis Bach

Regularized reconstruction error enables auto-encoders to learn local features of data distribution, estimating gradients and Hessian matrices.

Guillaume Alain, Yoshua Bengio

Vovk extends inductive conformal prediction to conditional guarantees and proves that exact object-conditional validity is generally inefficient.

Vladimir Vovk

Combining optimal transport and quantization, the paper derives convergence bounds for learning probability measures supported on manifolds, achieving rates of n^{-1/(2d+4)}.

Guillermo D. Canas, Lorenzo Rosasco

Explores causal learning's impact on semi-supervised learning with hypotheses and validation.

Bernhard Schoelkopf, Dominik Janzing, Jonas Peters et al.

Deep learning-based representation learning, using autoencoders and probabilistic models, enhances feature extraction and model generalization.

Yoshua Bengio, Aaron Courville, Pascal Vincent

Proposes a nonparametric RKHS embedding approach for modeling MDP transition dynamics, outperforming Gaussian processes and NPDP in efficiency and accuracy.

Steffen Grunewalder, Guy Lever, Luca Baldassarre et al.

Proposes a training-data-driven expert learning algorithm with context trees for improved short-sequence prediction.

Elad Eban, Aharon Birnbaum, Shai Shalev-Shwartz et al.