arXiv research

The paper analyzes security issues in blockchain ecosystems with multiple SSPs and proposes two models for better stake management.

Over the last decade, digital media (web or app publishers) generalized the use of real time ad auctions to sell their ad spaces. Multiple auction platforms, also called Supply-Side Platforms (SSP), were created. Because of this multiplicity, publishers started to create competition between SSPs. In this setting, there…

Paper introduces data-dependent SSP for private linear and logistic regression.

Many popular reinforcement learning problems (e.g., navigation in a maze, some Atari games, mountain car) are instances of the episodic setting under its stochastic shortest path (SSP) formulation, where an agent has to achieve a goal state while minimizing the cumulative cost. Despite the popularity of this setting, t…

Deep learning is a popular machine learning technique and has been applied to many real-world problems. However, training a deep neural network is very time-consuming, especially on big data. It has become difficult for a single machine to train a large model over large datasets. A popular solution is to distribute and…

New algorithms for planning with adversarial changes in costs.

New algorithms reduce dynamic regret in online MDPs with changing losses.

Algorithm reduces regret in SSP problems with LFA.

Study shows sample complexity for learning optimal policies in SSP with generative model.

Study shows hard sample complexity for learning optimal policies in stochastic shortest path problems.

New algorithm learns optimal path in reinforcement learning with linear approximations.

Enhances DP linear regression using public data moments.

New algorithms minimize regret in SSP with optimal sparse updates.

Unified algorithm for optimizing rewards in stochastic path problems.

Paper tackles offline SSP with value iteration for policy evaluation and learning.

We study a risk-constrained version of the stochastic shortest path (SSP) problem, where the risk measure considered is Conditional Value-at-Risk (CVaR). We propose two algorithms that obtain a locally risk-optimal policy by employing four tools: stochastic approximation, mini batches, policy gradients and importance s…

New algorithm reduces regret in linear mixture SSPs without cost bounds.

New method reduces regret for sparse adversarial SSP problems.

Study on private algorithms for saddle point and variational inequalities, improving efficiency and applicability.

Paper identifies reductive MDPs, solving them in polynomial time.

Q-learning for average cost MDPs gets a concentration bound.

Two new algorithms solve privacy-constrained SVI and SSP problems.

High signal to noise ratio (SNR) consistency of model selection criteria in linear regression models has attracted a lot of attention recently. However, most of the existing literature on high SNR consistency deals with model order selection. Further, the limited literature available on the high SNR consistency of subs…

Two new algorithms solve nonconvex-strongly concave problems efficiently.

Paper evaluates robustness of NAS against poisoning attacks.

Bayesian framework for SSP problem learns optimal strategy through interactions.

Gaussian beams describe the amplitude and phase of rays and are widely used to model acoustic propagation. This paper describes four new results in the theory of Gaussian beams. (1) A new version of the Červený equations for the amplitude and phase of Gaussian beams is developed by applying the equivalence of Hamilton-…

We propose a distributed approach to train deep neural networks (DNNs), which has guaranteed convergence theoretically and great scalability empirically: close to 6 times faster on instance of ImageNet data set when run with 6 machines. The proposed scheme is close to optimally scalable in terms of number of machines, …

New bid shading algorithm reduces costs by 55%.

Stochastic shortest path (SSP) is a well-known problem in planning and control, in which an agent has to reach a goal state in minimum total expected cost. In the learning formulation of the problem, the agent is unaware of the environment dynamics (i.e., the transition function) and has to repeatedly play for a given …

Deep network optimizes ad bidding for first-price auctions.

New bounds for SA with arbitrary norm contractions and Markovian noise.

DS-Sync improves distributed DNN training efficiency by 94% with minimal accuracy loss.

Bayesian approach infers signaling pathways from data.

Credit risk management in Italy is characterized, in the period June 2008 to June 2012, by frequent (frequency=0.5 cycles per year) and intense (peak amplitude: mean=39.2 billion Euros, s.e.=2.83 billion Euros) quarterly contractions and expansions around the mean (915.4 billion Euros, s.e.=3.59 billion Euros) of the n…

Paper proves Pareto efficient insurance for multiple entities.

Study of multiplicative connections in Lie groupoids.

Study rectifying curves in 3D multiplicative Euclidean space.

The paper classifies symmetric triads with multiplicities and their applications.

New method identifies proxies for causal effects on multiple outcomes.

We define a concept which we call multiplicity. First, multiplicity of a morphism is defined. Then the multiplicity of an object over another object is defined to be the minimum of the multiplicities of all morphisms from one to another. Based on this multiplicity, we define a pseudo distance on the class of objects. W…

We introduce a multiple conjugation biquandle, and show that it is the universal algebra to define a semi-arc coloring invariant for handlebody-links. A multiple conjugation biquandle is a generalization of a multiple conjugation quandle. We extend the notion of $n$-parallel biquandle operations for any integer $n$, an…

Study finds methods to learn multiple solutions from single task in offline RL.

Let $(M,ω)$ be a connected symplectic manifold on which a connected Lie group $G$ acts properly and in a Hamiltonian fashion with moment map $μ:M \lra \mf g^*$. Our purpose is investigate multiplicity-free actions, giving criteria to decide a multiplicity freenes of the action. As an application we give the complete cl…

MKLpy simplifies Multiple Kernel Learning in Python.

Recently neural networks and multiple instance learning are both attractive topics in Artificial Intelligence related research fields. Deep neural networks have achieved great success in supervised learning problems, and multiple instance learning as a typical weakly-supervised learning method is effective for many app…

X-SHAP assesses multiplicative variable contributions in machine learning models.

New infinite-dimensional representations with bounded multiplicity found for Lie groups.