Quantum states enable publicly-verifiable quantum money and quantum copy-protection.

Scott Aaronson

Proves exponential tail bounds for quadratic forms of subgaussian vectors, analogous to Gaussian case, with explicit constants.

Daniel Hsu, Sham M. Kakade, Tong Zhang

Proposes a bias-corrected low-dimensional projection (LDPE) method for constructing confidence intervals in high-dimensional linear models, effective without uniform signal strength assumptions.

Cun-Hui Zhang, Stephanie S. Zhang

Analysis of 0-1 loss reveals superior noise tolerance, especially under non-uniform label noise, with theoretical guarantees and empirical validation.

Naresh Manwani, P. S. Sastry

Machine learning model predicts molecular atomization energies with ~10 kcal/mol MAE, using nuclear charges and atomic positions, enabling rapid large-scale energy estimation.

Matthias Rupp, Alexandre Tkatchenko, Klaus-Robert Müller et al.

Proposes a model-free, weighted risk-sensitive RL algorithm balancing reward and error state probability, validated on continuous and discrete control tasks.

P. Geibel, F. Wysotzki

Perseus: a randomized point-based value iteration method for large-scale POMDPs, improving efficiency with belief subset sampling

M. T. J. Spaan, N. Vlassis

Proposes Gossip learning with linear models using random walks and model averaging, enabling privacy-preserving, low-communication distributed classification.

Róbert Ormándi, István Hegedüs, Márk Jelasity

Proposes a Bayesian simulation-based optimal experimental design framework combining Polynomial Chaos and stochastic approximation, improving efficiency in nonlinear systems.

Xun Huan, Youssef M. Marzouk

Using GGA+U with U=1.9 eV, J=1.2 eV, accurately reproduces low-temperature intrinsic anomalous Hall conductivity of nickel, matching experimental data.

Huei-Ru Fuh, Guang-Yu Guo

Introduces quantum annealing and quantum stochastic optimization, demonstrating improved heuristics for NP-hard problems with experimental validation.

Diego de Falco, Dario Tamascelli

Grounded Semantic Composition on Bishop: 59% correct referent selection.

P. Gorniak, D. Roy

Proposed a distributed reactive power compensation strategy using a randomized Gossip algorithm, achieving significant power loss reduction in smart microgrids.

Saverio Bolognani, Sandro Zampieri

SMOTE: Synthetic Minority Over-sampling Technique improves classifier performance on imbalanced datasets by generating synthetic minority samples, boosting AUC by over 0.07 in various experiments.

N. V. Chawla, K. W. Bowyer, L. O. Hall et al.

Proposes a strategy for continuum-armed bandits without knowing the Lipschitz constant, achieving optimal regret bounds.

Sébastien Bubeck, Gilles Stoltz, Jia Yuan Yu

The paper proposes minimax policies for combinatorial prediction games using Bregman projections and potential-based gradient descent to address worst-case minimax regret.

Jean-Yves Audibert, Sebastien Bubeck, Gabor Lugosi

Introduces RFCI, a fast algorithm for high-dimensional causal graph learning with latent and selection variables, ensuring asymptotic correctness.

Diego Colombo, Marloes H. Maathuis, Markus Kalisch et al.

Proposes column subset-based low-rank matrix reconstruction achieving an optimal Frobenius norm approximation ratio of \(\sqrt{rac{r+1}{r-k+1}}\), with algorithms running in O(r n m^ω log m).

Venkatesan Guruswami, Ali Kemal Sinop

Proposes a unified neural network framework leveraging large-scale unlabeled data for multiple NLP tasks, achieving state-of-the-art results without task-specific engineering.

Ronan Collobert, Jason Weston, Leon Bottou et al.

The KL-UCB algorithm outperforms UCB in bounded stochastic bandits, achieving optimal bounds in Bernoulli rewards.

Aurélien Garivier, Olivier Cappé