arXiv research

Framework infers coordination strategies from movement data.

We propose and analyze a new parallel coordinate descent method---`NSync---in which at each iteration a random subset of coordinates is updated, in parallel, allowing for the subsets to be chosen non-uniformly. We derive convergence rates under a strong convexity assumption, and comment on how to assign probabilities t…

RL optimizes resource allocation in MG by balancing experience and exploration.

Adapts agent strategies on-the-fly for better cross-play in cooperative settings.

Proposes a neural network method to correct residual distortions in coordinate transformations.

Paper speeds up tensor factorization algorithms.

We in this paper propose a realizable framework TECU, which embeds task-specific strategies into update schemes of coordinate descent, for optimizing multivariate non-convex problems with coupled objective functions. On one hand, TECU is capable of improving algorithm efficiencies through embedding productive numerical…

Study uses reinforcement learning to optimize metachronal paddling at low Reynolds number.

Agents learn sophisticated tool use and coordination in hide-and-seek.

The paper accelerates regression algorithms by identifying saturated coordinates.

To answer the existence of optimal swimmer learning/teaching strategies, this work introduces a two-level clustering in order to analyze temporal dynamics of motor learning in breaststroke swimming. Each level have been performed through Sparse Fisher-EM, a unsupervised framework which can be applied efficiently on lar…

New SGD method uses adaptive sampling to converge faster in non-convex problems.

Coordinate descent with random coordinate selection is the current state of the art for many large scale optimization problems. However, greedy selection of the steepest coordinate on smooth problems can yield convergence rates independent of the dimension $n$, and requiring upto $n$ times fewer iterations. In this pap…

Paper speeds up IoT device detection and data decoding.

In multi-agent reinforcement learning, discovering successful collective behaviors is challenging as it requires exploring a joint action space that grows exponentially with the number of agents. While the tractability of independent agent-wise exploration is appealing, this approach fails on tasks that require elabora…

In recent years, state-of-the-art methods for supervised learning have exploited increasingly gradient boosting techniques, with mainstream efficient implementations such as xgboost or lightgbm. One of the key points in generating proficient methods is Feature Selection (FS). It consists in selecting the right valuable…

LOCA learns standardized data coordinates from measurements.

In this article, we present a brief narration of the origin and the overview of the recent developments done on the Kolkata Paise Restaurant (KPR) problem, which can serve as a prototype for a broader class of resource allocation problems in the presence of a large number of competing agents, typically studied using co…

New method for decentralized learning reduces data and computation needs.

Picasso is a new library for sparse learning problems in R and Python.

New method reduces variance in random coordinate descent for Langevin Monte Carlo.

In representation learning and non-linear dimension reduction, there is a huge interest to learn the 'disentangled' latent variables, where each sub-coordinate almost uniquely controls a facet of the observed data. While many regularization approaches have been proposed on variational autoencoders, heuristic tuning is …

Study improves model robustness in noisy datasets.

This work investigates the training of conditional random fields (CRFs) via the stochastic dual coordinate ascent (SDCA) algorithm of Shalev-Shwartz and Zhang (2016). SDCA enjoys a linear convergence rate and a strong empirical performance for binary classification problems. However, it has never been used to train CRF…

The omnipresence of deep learning architectures such as deep convolutional neural networks (CNN)s is fueled by the synergistic combination of ever-increasing labeled datasets and specialized hardware. Despite the indisputable success, the reliance on huge amounts of labeled data and specialized hardware can be a limiti…

We develop a more efficient NGD method for structured parameters.

Paper tackles inventory management with deep learning, improving performance and adherence to constraints.

We consider the problem of distributed dictionary learning, where a set of nodes is required to collectively learn a common dictionary from noisy measurements. This approach may be useful in several contexts including sensor networks. Diffusion cooperation schemes have been proposed to solve the distributed linear regr…

Develops a fast algorithm for high-dimensional LASSO penalized quantile regression.

Whenever customers' choices (e.g. to buy or not a given good) depend on others choices (cases coined 'positive externalities' or 'bandwagon effect' in the economic literature), the demand may be multiply valued: for a same posted price, there is either a small number of buyers, or a large one -- in which case one says …

We propose a method to efficiently learn diverse strategies in reinforcement learning for query reformulation in the tasks of document retrieval and question answering. In the proposed framework an agent consists of multiple specialized sub-agents and a meta-agent that learns to aggregate the answers from sub-agents to…

Recently, new defense techniques have been developed to tolerate Byzantine failures for distributed machine learning. The Byzantine model captures workers that behave arbitrarily, including malicious and compromised workers. In this paper, we break two prevailing Byzantine-tolerant techniques. Specifically we show robu…

Algorithm reduces regret in multi-player bandits with unknown collision rewards.

Paper details Hilbert-curve for high-performance data mining.

HedgeAgents boosts financial trading with balanced strategies.

This paper proposes a decentralized reinforcement learning method for multi-agent resource allocation.

New algorithms solve nonconvex federated learning problems efficiently.

DiPCA algorithm improves scalability and solution quality for time-dependent data.

ARCO-BO optimizes multi-agent design under heterogeneity, improving efficiency and performance.

New framework for multi-agent reinforcement learning improves coordination and efficiency.

This paper is a sequel of arxiv:1709.09045 and deals with privileged coordinates and nilpotent approximation of Carnot manifolds. By a Carnot manifold it is meant a manifold equipped with a filtration by subbundles of the tangent bundle which is compatible with the Lie bracket of vector fields. In this paper, we single…

Leveraging on the convexity of the Lasso problem , screening rules help in accelerating solvers by discarding irrelevant variables, during the optimization process. However, because they provide better theoretical guarantees in identifying relevant variables, several non-convex regularizers for the Lasso have been prop…

Coordinate descent methods usually minimize a cost function by updating a random decision variable (corresponding to one coordinate) at a time. Ideally, we would update the decision variable that yields the largest decrease in the cost function. However, finding this coordinate would require checking all of them, which…

Two non-communicating players minimize regret in a multi-armed bandit game.

MountainLion uses LLMs to interpret financial data and generate investment strategies.

New findings on Kähler manifolds restrict orthogonal coordinates existence.

Defines Fenchel-Nielsen coordinates for SL(3,C) representations.

Submanifolds of coordinate finite-type were introduced in HV1. A submanifold of a Euclidean space is called a coordinate finite-type submanifold if its coordinate functions are eigenfunctions of Δ. In the present study we consider coordinate finite-type surfaces in E^4. We give necessary and sufficient conditions for g…