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 on learning rates in neural networks of varying depth.
The paper analyzes generalization of noisy, iterative algorithms using maximal leakage.
Study on maximizing submodular functions with limited updates, achieving tight bounds and poly-time algorithms.
Unified learning-rate scale for CNNs and ResNets, avoiding depth imbalance.
Paper improves policy updates in reinforcement learning to speed up learning.
Efficiently maximizes AUC with deep nets, reducing communication rounds.
New algorithm for maximizing submodular functions in real-time data changes.
FavMac maximizes value while controlling cost in multi-label prediction.
Many policy gradient methods are variants of Actor-Critic (AC), where a value function (critic) is learned to facilitate updating the parameterized policy (actor). The update to the actor involves a log-likelihood update weighted by the action-values, with the addition of entropy regularization for soft variants. In th…
Robust state-space radio interferometric imaging using Stochastic Approximation Expectation Maximization
Framework for safely updating machine learning models.
Constrained Markov Decision Process (CMDP) is a natural framework for reinforcement learning tasks with safety constraints, where agents learn a policy that maximizes the long-term reward while satisfying the constraints on the long-term cost. A canonical approach for solving CMDPs is the primal-dual method which updat…
We describe -MLE, a fast and efficient local search algorithm for learning finite statistical mixtures of exponential families such as Gaussian mixture models. Mixture models are traditionally learned using the expectation-maximization (EM) soft clustering technique that monotonically increases the incomplete (expec…
The paper analyzes when credal sets stabilize under iterative updates in machine learning.
The back-propagation algorithm is the cornerstone of deep learning. Despite its importance, few variations of the algorithm have been attempted. This work presents an approach to discover new variations of the back-propagation equation. We use a domain specific lan- guage to describe update equations as a list of primi…
Although modern recommendation systems can exploit the structure in users' item feedback, most are powerless in the face of new users who provide no structure for them to exploit. In this paper we introduce ImplicitCE, an algorithm for recommending items to new users during their sign-up flow. ImplicitCE works by trans…
Graph Neural Networks (GNNs) achieve an impressive performance on structured graphs by recursively updating the representation vector of each node based on its neighbors, during which parameterized transformation matrices should be learned for the node feature updating. However, existing propagation schemes are far fro…
Federated learning can be vulnerable to adversarial attacks, which this work addresses.
Actor-critic methods solve reinforcement learning problems by updating a parameterized policy known as an actor in a direction that increases an estimate of the expected return known as a critic. However, existing actor-critic methods only use values or gradients of the critic to update the policy parameter. In this pa…
SDPA is shown to be an optimal transport problem in deep learning.
The paper deals with learning probability distributions of observed data by artificial neural networks. We suggest a so-called gradient conjugate prior (GCP) update appropriate for neural networks, which is a modification of the classical Bayesian update for conjugate priors. We establish a connection between the gradi…
Efficiently selects seed nodes to maximize content influence in unknown social networks.
Develops a Bayesian framework for portfolio choice with a new posterior distribution.
We present a two-stage approach for learning dictionaries for object classification tasks based on the principle of information maximization. The proposed method seeks a dictionary that is compact, discriminative, and generative. In the first stage, dictionary atoms are selected from an initial dictionary by maximizing…
In this paper, we study the problem of robust influence maximization in the independent cascade model under a hyperparametric assumption. In social networks users influence and are influenced by individuals with similar characteristics and as such, they are associated with some features. A recent surging research direc…
Integrates VAEs into EM for deep clustering and generation.
Two-Timescale EM Methods improve EM for nonconvex models.
Experience replay enables reinforcement learning agents to memorize and reuse past experiences, just as humans replay memories for the situation at hand. Contemporary off-policy algorithms either replay past experiences uniformly or utilize a rule-based replay strategy, which may be sub-optimal. In this work, we consid…
Deep learning achieves state-of-the-art results in many tasks in computer vision and natural language processing. However, recent works have shown that deep networks can be vulnerable to adversarial perturbations, which raised a serious robustness issue of deep networks. Adversarial training, typically formulated as a …
This paper quantifies hyperparameter transfer and finds embedding layer learning rate is key.
A new principle for optimizer selection improves training speed and performance.
Recent literature has demonstrated promising results for training Generative Adversarial Networks by employing a set of discriminators, in contrast to the traditional game involving one generator against a single adversary. Such methods perform single-objective optimization on some simple consolidation of the losses, e…
New algorithm optimizes auction prices in real-time.
A novel minimax classifier tackles imbalanced datasets with few minority samples.
New algorithms reduce matching regret by limiting frequent updates.
This paper analyzes implicit bias in Deep Linear Discriminant Analysis.
Proposes a new sampling method for online learning with cumulative oversampling.
Expectation-Maximization (EM) is a prominent approach for parameter estimation of hidden (aka latent) variable models. Given the full batch of data, EM forms an upper-bound of the negative log-likelihood of the model at each iteration and updates to the minimizer of this upper-bound. We first provide a "model level" in…
New method improves neural network training by scaling perturbations layerwise.
Previous studies on stochastic primal-dual algorithms for solving min-max problems with faster convergence heavily rely on the bilinear structure of the problem, which restricts their applicability to a narrowed range of problems. The main contribution of this paper is the design and analysis of new stochastic primal-d…
Modern reinforcement learning algorithms reach super-human performance on many board and video games, but they are sample inefficient, i.e. they typically require significantly more playing experience than humans to reach an equal performance level. To improve sample efficiency, an agent may build a model of the enviro…
Generative Adversarial Nets (GANs) represent an important milestone for effective generative models, which has inspired numerous variants seemingly different from each other. One of the main contributions of this paper is to reveal a unified geometric structure in GAN and its variants. Specifically, we show that the ad…
Information-Geometric Optimization (IGO) is a unified framework of stochastic algorithms for optimization problems. Given a family of probability distributions, IGO turns the original optimization problem into a new maximization problem on the parameter space of the probability distributions. IGO updates the parameter …
This paper shows how deep neural networks can learn rich, independent features that significantly deviate from initialization.
Forward stagewise regression follows a very simple strategy for constructing a sequence of sparse regression estimates: it starts with all coefficients equal to zero, and iteratively updates the coefficient (by a small amount ) of the variable that achieves the maximal absolute inner product with the current residua…
We develop a novel method for training of GANs for unsupervised and class conditional generation of images, called Linear Discriminant GAN (LD-GAN). The discriminator of an LD-GAN is trained to maximize the linear separability between distributions of hidden representations of generated and targeted samples, while the …
Paper tackles multi-block min-max optimization with applications in deep AUC maximization.
Regularized EM algorithm improves GMM clustering in low sample settings.