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.
A new method for efficient neural network fine-tuning using queryable low-rank update atoms.
Two algorithms for linear contextual bandits with rare updates achieve optimal regret and efficiency.
Framework for safely updating machine learning models.
In several recently proposed stochastic optimization methods (e.g. RMSProp, Adam, Adadelta), parameter updates are scaled by the inverse square roots of exponential moving averages of squared past gradients. Maintaining these per-parameter second-moment estimators requires memory equal to the number of parameters. For …
Study on rich regime training in deep learning, finding active parameters in bottom layers.
A new FL algorithm reduces communication overhead by selectively updating model parameters.
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…
Here, we study different update rules in stochastic gradient descent (SGD) for online forecasting problems. The selection of the learning rate parameter is critical in SGD. However, it may not be feasible to tune this parameter in online learning. Therefore, it is necessary to have an update rule that is not sensitive …
Improved HGF networks avoid negative precision errors in volatility updates.
A new update rule for deep reinforcement learning reduces learning variance and variance in reference signals.
Synthetic data replaces model updates in federated learning.
For a long investment time horizon, it is preferable to rebalance the portfolio weights at intermediate times. This necessitates a multi-period market model in which portfolio optimization is usually done through dynamic programming. However, this assumes a known distribution for the parameters of the financial time se…
Gradient-based methods introduce noise that penalizes models sensitive to weight perturbations.
Meta-learning consists in learning learning algorithms. We use a Long Short Term Memory (LSTM) based network to learn to compute on-line updates of the parameters of another neural network. These parameters are stored in the cell state of the LSTM. Our framework allows to compare learned algorithms to hand-made algorit…
The ubiquitous use of machine learning algorithms brings new challenges to traditional database problems such as incremental view update. Much effort is being put in better understanding and debugging machine learning models, as well as in identifying and repairing errors in training datasets. Our focus is on how to as…
Test-time training adapts a pretrained model to each prompt via parameter updates, improving accuracy under pretraining-to-test distribution shifts.
Most of the recent successful applications of neural networks have been based on training with gradient descent updates. However, for some small networks, other mirror descent updates learn provably more efficiently when the target is sparse. We present a general framework for casting a mirror descent update as a gradi…
CAdam optimizes online learning by adapting to distribution shifts and noise.
Study reveals convergence properties of SGD with random learning rate.
New algorithm uses PSO to optimize DNN training parameters in distributed systems.
New algorithm closes empirical gap in PFSGD performance.
New PG samplers improve inference in coupled state-space models.
Traditionally, deep learning algorithms update the network weights whereas the network architecture is chosen manually, using a process of trial and error. In this work, we propose two novel approaches that automatically update the network structure while also learning its weights. The novelty of our approach lies in o…
Iterative procedures for parameter estimation based on stochastic gradient descent allow the estimation to scale to massive data sets. However, in both theory and practice, they suffer from numerical instability. Moreover, they are statistically inefficient as estimators of the true parameter value. To address these tw…
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…
Adaptive sparse GP model for non-stationary data.
FiT combines transfer and meta-learning for efficient few-shot image classification.
Transformers can implement reinforcement learning algorithms from data without updates.
This paper re-examines the problem of parameter estimation in Bayesian networks with missing values and hidden variables from the perspective of recent work in on-line learning [Kivinen & Warmuth, 1994]. We provide a unified framework for parameter estimation that encompasses both on-line learning, where the model is c…
GANs excel at learning high dimensional distributions, but they can update generator parameters in directions that do not correspond to the steepest descent direction of the objective. Prominent examples of problematic update directions include those used in both Goodfellow's original GAN and the WGAN-GP. To formally d…
Block Coordinate Update (BCU) methods enjoy low per-update computational complexity because every time only one or a few block variables would need to be updated among possibly a large number of blocks. They are also easily parallelized and thus have been particularly popular for solving problems involving large-scale …
This work introduces a fixed-point optimization for variational inference.
DualAdam improves generalization of Adam by integrating its update mechanisms.
The (stochastic) gradient descent and the multiplicative update method are probably the most popular algorithms in machine learning. We introduce and study a new regularization which provides a unification of the additive and multiplicative updates. This regularization is derived from an hyperbolic analogue of the entr…
Optimization algorithms with momentum, e.g., (ADAM), have been widely used for building deep learning models due to the faster convergence rates compared with stochastic gradient descent (SGD). Momentum helps accelerate SGD in the relevant directions in parameter updating, which can minify the oscillations of parameter…
LDP-Fed protects privacy in federated learning with neural networks.
New optimizer designs respect symmetry, improving deep learning models.
Bayesian model updating uses VAEs to approximate likelihood with small data.
In this paper we revisit the weighted likelihood bootstrap, a method that generates samples from an approximate Bayesian posterior of a parametric model. We show that the same method can be derived, without approximation, under a Bayesian nonparametric model with the parameter of interest defined as minimising an expec…
In this paper we apply active learning algorithms for dynamic pricing in a prominent e-commerce website. Dynamic pricing involves changing the price of items on a regular basis, and uses the feedback from the pricing decisions to update prices of the items. Most popular approaches to dynamic pricing use a passive learn…
Fewer data weight updates lead to faster convergence in machine learning models.
The present paper proposes generalized Gaussian kernel adaptive filtering, where the kernel parameters are adaptive and data-driven. The Gaussian kernel is parametrized by a center vector and a symmetric positive definite (SPD) precision matrix, which is regarded as a generalization of the scalar width parameter. These…
Model analyzes cooccurrence data for recommender systems and item relevance.
Stochastic gradient descent procedures have gained popularity for parameter estimation from large data sets. However, their statistical properties are not well understood, in theory. And in practice, avoiding numerical instability requires careful tuning of key parameters. Here, we introduce implicit stochastic gradien…
GENIE balances domain-invariant feature learning and gradient alignment for improved DG performance.
dYdX updates liquidity provider incentives to enhance trading efficiency.
We develop methods for parameter estimation in settings with large-scale data sets, where traditional methods are no longer tenable. Our methods rely on stochastic approximations, which are computationally efficient as they maintain one iterate as a parameter estimate, and successively update that iterate based on a si…
In-Place TTT enhances LLMs with dynamic parameter updates at inference time.