gabrieldernbach

from dataclasses import dataclass, replace
from joblib import Parallel, delayed
from typing import Optional, Callable, List, Iterable

@dataclass(frozen=True)
class Either:
    value: Optional = None
    exception: Optional = None
        
def forward_exceptions(fun: Callable):

gabrieldernbach

# leverage scores l_[i] = tr(X @ (X^T X)^-1 @ X)
# indication of self-sensitivity or self-influence of i-th sample.
import numpy as np

n = 2048 # samples
d = 256 # dimensions
X = np.random.randn(n, d) # design matrix

# navie computation, high memory footprint (quadtratic in n^2) 
l_naive = np.trace(X @ np.linalg.inv(X) @ X)

gabrieldernbach

import torch
import torch.nn as nn
from sklearn.datasets import make_moons
from tqdm import tqdm
import matplotlib.pyplot as plt

class Flow(nn.Module):
    def __init__(self, n_dim=2, n_pos_dim=2, n_hidden=64):
        super().__init__()
        self.n_dim = n_dim

gabrieldernbach

class MINE(nn.Module):
    """
    Stub to implement Mutual Information Neural Estimation.
    See https://arxiv.org/pdf/1801.04062
    
    Quote: 
    We argue that the estimation of mutual information 
    between high dimensional continuous random variables can be 
    achieved by gradient descent over neural networks. We present a