A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Study predicts academic achievement using students' support networks.
New algorithm reduces individual regret and communication costs in cooperative bandits.
Community detection is a fundamental statistical problem in network data analysis. Many algorithms have been proposed to tackle this problem. Most of these algorithms are not guaranteed to achieve the statistical optimality of the problem, while procedures that achieve information theoretic limits for general parameter…
LEXA learns to discover and achieve goals in unseen environments.
Max entropy exploration guides reinforcement learning agents to pursue achievable goals.
New coding theorem shows achievable rate matches theoretical limit.
Improved deep kernel machine achieves 94.5% test accuracy on CIFAR-10.
ProxSkip achieves linear speedup in distributed non-convex optimization.
Achieved all-orders worldline action for Kerr black hole.
This is the Proceedings of NeurIPS 2018 Workshop on Machine Learning for the Developing World: Achieving Sustainable Impact, held in Montreal, Canada on December 8, 2018
Gradient descent benefits from tangent kernel advantages under specific conditions.
We show through case studies that it is easier to estimate the fundamental limits of data processing than to construct explicit algorithms to achieve those limits. Focusing on binary classification, data compression, and prediction under logarithmic loss, we show that in the finite space setting, when it is possible to…
Langevin DQN achieves deep exploration using Gaussian noise.
Paper establishes identifiability and achievability for causal representation learning.
We introduce Minimal Achievable Sufficient Statistic (MASS) Learning, a training method for machine learning models that attempts to produce minimal sufficient statistics with respect to a class of functions (e.g. deep networks) being optimized over. In deriving MASS Learning, we also introduce Conserved Differential I…
How can we make machine learning provably robust against adversarial examples in a scalable way? Since certified defense methods, which ensure -robust, consume huge resources, they can only achieve small degree of robustness in practice. Lipschitz margin training (LMT) is a scalable certified defense, but it can als…
New algorithms achieve optimal DP convex optimization with linear time and gradient computations.
Recurrent Neural Networks (RNN), Long Short-Term Memory Networks (LSTM), and Memory Networks which contain memory are popularly used to learn patterns in sequential data. Sequential data has long sequences that hold relationships. RNN can handle long sequences but suffers from the vanishing and exploding gradient probl…
A statistical analysis of financial, economic, and demographic indicators performed by the authors demonstrates (1) that the main countries of East Africa (Uganda, Kenya, and Tanzania) have not escaped the Malthusian Trap yet; (2) that this countries are not likely to follow the "North African path" and to achieve this…
This paper tackles causal representation learning with linear and general transformations.
Machine learning is used to compute achievable information rates (AIRs) for a simplified fiber channel. The approach jointly optimizes the input distribution (constellation shaping) and the auxiliary channel distribution to compute AIRs without explicit channel knowledge in an end-to-end fashion.
A new method MixGDA combines mixup and gradient-based data augmentation for SSL.
Simplified image clustering achieves competitive results without text-based embeddings.
Representation learning, especially which by using deep learning, has been widely applied in classification. However, how to use limited size of labeled data to achieve good classification performance with deep neural network, and how can the learned features further improve classification remain indefinite. In this pa…
New learning rules achieve optimal sample complexity for weakly supervised classification.
Conditional gradients constitute a class of projection-free first-order algorithms for smooth convex optimization. As such, they are frequently used in solving smooth convex optimization problems over polytopes, for which the computational cost of orthogonal projections would be prohibitive. However, they do not enjoy …
This paper proposes BRIEF, a backward reduction algorithm that explores compact CNN-model designs from the information flow perspective. This algorithm can remove substantial non-zero weighting parameters (redundant neural channels) of a network by considering its dynamic behavior, which traditional model-compaction te…
The study of curvature in spacelike submanifolds in pseudo-hyperbolic spaces.
Recent theoretical work has guaranteed that overparameterized networks trained by gradient descent achieve arbitrarily low training error, and sometimes even low test error. The required width, however, is always polynomial in at least one of the sample size , the (inverse) target error , and the (inverse) fail…
New computational lower bounds for clustering and related problems.
Distance metric learning (DML), which learns a distance metric from labeled "similar" and "dissimilar" data pairs, is widely utilized. Recently, several works investigate orthogonality-promoting regularization (OPR), which encourages the projection vectors in DML to be close to being orthogonal, to achieve three effect…
Decentralized optimization algorithms have attracted intensive interests recently, as it has a balanced communication pattern, especially when solving large-scale machine learning problems. Stochastic Path Integrated Differential Estimator Stochastic First-Order method (SPIDER-SFO) nearly achieves the algorithmic lower…
In large-scale distributed learning, security issues have become increasingly important. Particularly in a decentralized environment, some computing units may behave abnormally, or even exhibit Byzantine failures -- arbitrary and potentially adversarial behavior. In this paper, we develop distributed learning algorithm…
New algorithms achieve optimal regret in sliding window model with limited memory.
We present a new anytime algorithm that achieves near-optimal regret for any instance of finite stochastic partial monitoring. In particular, the new algorithm achieves the minimax regret, within logarithmic factors, for both "easy" and "hard" problems. For easy problems, it additionally achieves logarithmic individual…
A good representation for arbitrarily complicated data should have the capability of semantic generation, clustering and reconstruction. Previous research has already achieved impressive performance on either one. This paper aims at learning a disentangled representation effective for all of them in an unsupervised way…
New algorithms improve linear bandit performance with low computation.
Stochastic Gradient Langevin Dynamics infuses isotropic gradient noise to SGD to help navigate pathological curvature in the loss landscape for deep networks. Isotropic nature of the noise leads to poor scaling, and adaptive methods based on higher order curvature information such as Fisher Scoring have been proposed t…
New method improves training-free guidance for diffusion models, achieving state-of-the-art results.
Resolving a conjecture of Abbe, Bandeira and Hall, the authors have recently shown that the semidefinite programming (SDP) relaxation of the maximum likelihood estimator achieves the sharp threshold for exactly recovering the community structure under the binary stochastic block model of two equal-sized clusters. The s…
In Multi-Goal Reinforcement Learning, an agent learns to achieve multiple goals with a goal-conditioned policy. During learning, the agent first collects the trajectories into a replay buffer, and later these trajectories are selected randomly for replay. However, the achieved goals in the replay buffer are often biase…
This work achieves exponential concentration in heavy-tailed data over CAT(κ) spaces using the Fréchet median.
ADSGD method speeds up model identification in sparse optimization.
Smart beta, also known as strategic beta or factor investing, is the idea of selecting an investment portfolio in a simple rule-based manner that systematically captures market inefficiencies, thereby enhancing risk-adjusted returns above capitalization-weighted benchmarks. We explore the idea of applying a smart strat…
New algorithm achieves both static and dynamic regret optimally against an oblivious adversary for deterministic losses.
GCAE uses density estimation to achieve reliable disentanglement in latent space.
We propose a simple and easy to implement neural network compression algorithm that achieves results competitive with more complicated state-of-the-art methods. The key idea is to modify the original optimization problem by adding K independent Gaussian priors (corresponding to the k-means objective) over the network p…
We study the statistical and computational aspects of kernel principal component analysis using random Fourier features and show that under mild assumptions, features suffices to achieve sample complexity. Furthermore, we give a memory efficient streaming algorithm based on classical Oja…