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.
Survey of integrating physics knowledge into machine learning models.
PhysVarMix predicts diverse urban trajectories with physics constraints.
Develops experimental design for discovering missing physics in bioreactors.
We propose a method to model multi-agent behaviors with limited observation and mechanical constraints.
Single model learns physics from diverse data.
There is significant interest in using modern neural networks for scientific applications due to their effectiveness in modeling highly complex, non-linear problems in a data-driven fashion. However, a common challenge is to verify the scientific plausibility or validity of outputs predicted by a neural network. This w…
Physics-informed neural networks improve model accuracy and efficiency.
This paper proposes an in-depth re-thinking of neural computation that parallels apparently unrelated laws of physics, that are formulated in the variational framework of the least action principle. The theory holds for neural networks that are also based on any digraph, and the resulting computational scheme exhibits …
Bayesian symbolic regression automates model discovery from data.
Deep learning has achieved astonishing results on many tasks with large amounts of data and generalization within the proximity of training data. For many important real-world applications, these requirements are unfeasible and additional prior knowledge on the task domain is required to overcome the resulting problems…
We present a novel approach to weakly supervised object detection. Instead of annotated images, our method only requires two short videos to learn to detect a new object: 1) a video of a moving object and 2) one or more "negative" videos of the scene without the object. The key idea of our algorithm is to train the obj…
PhysicsFormer improves TSF models for GSWF with WEATHER-5K dataset.
aMCL uses annealing to improve hypothesis diversity in ambiguous tasks.
ARFs generate plausible counterfactuals for models, improving model understanding.
We develop a cross-sectional research design to identify causal effects in the presence of unobservable heterogeneity without instruments. When units are dense in physical space, it may be sufficient to regress the "spatial first differences" (SFD) of the outcome on the treatment and omit all covariates. The identifyin…
New method generates plausible counterfactuals for time series classification.
New non-semisimple Ising anyons enable robust universal quantum computation.
Method generates plausible financial stress scenarios using large deviations.
Optimism about the poorly understood states and actions is the main driving force of exploration for many provably-efficient reinforcement learning algorithms. We propose optimism in the face of sensible value functions (OFVF)- a novel data-driven Bayesian algorithm to constructing Plausibility sets for MDPs to explore…
AR algorithm simplifies backpropagation with improved scalability and biological plausibility.
The increasing deployment of machine learning as well as legal regulations such as EU's GDPR cause a need for user-friendly explanations of decisions proposed by machine learning models. Counterfactual explanations are considered as one of the most popular techniques to explain a specific decision of a model. While the…
New model separates objects in scenes, enabling novel arrangements and depth.
Derives a biologically plausible neural network for Slow Feature Analysis.
A principled approach to understand network structures is to formulate generative models. Given a collection of models, however, an outstanding key task is to determine which one provides a more accurate description of the network at hand, discounting statistical fluctuations. This problem can be approached using two p…
GAIT-prop derives a biologically plausible learning rule from backpropagation.
New learning rules from information bottleneck improve deep learning without precise labels.
Several techniques for domain adaptation have been proposed to account for differences in the distribution of the data used for training and testing. The majority of this work focuses on a binary domain label. Similar problems occur in a scientific context where there may be a continuous family of plausible data genera…
By and large, Backpropagation (BP) is regarded as one of the most important neural computation algorithms at the basis of the progress in machine learning, including the recent advances in deep learning. However, its computational structure has been the source of many debates on its arguable biological plausibility. In…
New method isolates epistemic uncertainty in diffusion models, improving plausibility scores.
Training deep neural networks with the error backpropagation algorithm is considered implausible from a biological perspective. Numerous recent publications suggest elaborate models for biologically plausible variants of deep learning, typically defining success as reaching around 98% test accuracy on the MNIST data se…
New algorithm shows neural networks can learn without full backpropagation.
A new method for robot manipulation tasks using imagined object goals.
Bayesian machine scientist uncovers accurate models from data.
Many real-world vision problems suffer from inherent ambiguities. In clinical applications for example, it might not be clear from a CT scan alone which particular region is cancer tissue. Therefore a group of graders typically produces a set of diverse but plausible segmentations. We consider the task of learning a di…
The Backpropagation algorithm relies on the abstraction of using a neural model that gets rid of the notion of time, since the input is mapped instantaneously to the output. In this paper, we claim that this abstraction of ignoring time, along with the abrupt input changes that occur when feeding the training set, are …
This note improves correlation stress tests using geodesic distance.
We propose to interpret distribution model risk as sensitivity of expected loss to changes in the risk factor distribution, and to measure the distribution model risk of a portfolio by the maximum expected loss over a set of plausible distributions defined in terms of some divergence from an estimated distribution. The…
One conjecture in both deep learning and classical connectionist viewpoint is that the biological brain implements certain kinds of deep networks as its back-end. However, to our knowledge, a detailed correspondence has not yet been set up, which is important if we want to bridge between neuroscience and machine learni…
Integrated Assessment Models (IAMs) are mainstay tools for assessing the long-term interactions between climate and the economy and for deriving optimal policy responses in the form of carbon prices. IAMs have been criticized for controversial discount rate assumptions, arbitrary climate damage functions, and the inade…
New learning algorithm mimics biological neural networks.
Automated suggestions help train technicians diagnose incidents faster.
New method uses entropy to generate multiple plausible causal maps.
Stock markets show unusual overnight and intraday returns.
Cold-start PV forecasting uses synthetic histories to train time-series foundation models.
Major histocompatibility complex class two (MHC-II) molecules are trans-membrane proteins and key components of the cellular immune system. Upon recognition of foreign peptides expressed on the MHC-II binding groove, helper T cells mount an immune response against invading pathogens. Therefore, mechanistic identificati…
In real world scenarios, objects are often partially occluded. This requires a robustness for object recognition against these perturbations. Convolutional networks have shown good performances in classification tasks. The learned convolutional filters seem similar to receptive fields of simple cells found in the prima…
The paper relaxes constraints on predictive coding models, making them more biologically plausible.
Model predicts unseen climate extremes to inform risk planning.