I am looking forward to learn the math behind the various optimizers present in neural networks such as adam,sgd,etc. Through this, I want to learn what makes one optimizer better than another for a particular case. Is anyone aware of resources that explain the math behind the various optimizer in deep learning?
2026-03-25 06:09:02.1774418942
Math behind various optimizers in deep learning
232 Views Asked by Bumbble Comm https://math.techqa.club/user/bumbble-comm/detail At
1
There are 1 best solutions below
Related Questions in REFERENCE-REQUEST
- Best book to study Lie group theory
- Alternative definition for characteristic foliation of a surface
- Transition from theory of PDEs to applied analysis and industrial problems and models with PDEs
- Random variables in integrals, how to analyze?
- Abstract Algebra Preparation
- Definition of matrix valued smooth function
- CLT for Martingales
- Almost locality of cubic spline interpolation
- Identify sequences from OEIS or the literature, or find examples of odd integers $n\geq 1$ satisfying these equations related to odd perfect numbers
- property of Lebesgue measure involving small intervals
Related Questions in OPTIMIZATION
- Optimization - If the sum of objective functions are similar, will sum of argmax's be similar
- optimization with strict inequality of variables
- Gradient of Cost Function To Find Matrix Factorization
- Calculation of distance of a point from a curve
- Find all local maxima and minima of $x^2+y^2$ subject to the constraint $x^2+2y=6$. Does $x^2+y^2$ have a global max/min on the same constraint?
- What does it mean to dualize a constraint in the context of Lagrangian relaxation?
- Modified conjugate gradient method to minimise quadratic functional restricted to positive solutions
- Building the model for a Linear Programming Problem
- Maximize the function
- Transform LMI problem into different SDP form
Related Questions in BOOK-RECOMMENDATION
- Books recommendations for a second lecture in functional analysis
- Book/Online Video Lectures/Notes Recommendation for Analysis(topics mentioned)
- Are there any analysis textbooks like Charles Pinter's A book of abstract algebra?
- Calculus book suggestion
- How to use the AOPS books?
- What are good books cover these topics?
- Book Recommendation: Introduction to probability theory (including stochastic processes)
- calculus of variations with double integral textbook?
- Probability that two random numbers have a Sørensen-Dice coefficient over a given threshold
- Algebraic geometry and algebraic topology used in string theory
Related Questions in MACHINE-LEARNING
- KL divergence between two multivariate Bernoulli distribution
- Can someone explain the calculus within this gradient descent function?
- Gaussian Processes Regression with multiple input frequencies
- Kernel functions for vectors in discrete spaces
- Estimate $P(A_1|A_2 \cup A_3 \cup A_4...)$, given $P(A_i|A_j)$
- Relationship between Training Neural Networks and Calculus of Variations
- How does maximum a posteriori estimation (MAP) differs from maximum likelihood estimation (MLE)
- To find the new weights of an error function by minimizing it
- How to calculate Vapnik-Chervonenkis dimension?
- maximize a posteriori
Related Questions in ONLINE-RESOURCES
- Online resources for networking and creating new mathematical collaborations
- Cryptocurrency Math
- Recent sets of notes/newly available online books on category theory?
- Is there a collaborative git repo for mathematical proofs?
- Are there any online resources that are freely availible, on Complex Analysis, that you recommend?
- Source of chapter
- Are there textbooks or resources on the mathematics of networks?
- Resources to make people understand the concepts of limits and continuity.
- Insightful educational games about mathematics?
- Coprime action of simple groups
Trending Questions
- Induction on the number of equations
- How to convince a math teacher of this simple and obvious fact?
- Find $E[XY|Y+Z=1 ]$
- Refuting the Anti-Cantor Cranks
- What are imaginary numbers?
- Determine the adjoint of $\tilde Q(x)$ for $\tilde Q(x)u:=(Qu)(x)$ where $Q:U→L^2(Ω,ℝ^d$ is a Hilbert-Schmidt operator and $U$ is a Hilbert space
- Why does this innovative method of subtraction from a third grader always work?
- How do we know that the number $1$ is not equal to the number $-1$?
- What are the Implications of having VΩ as a model for a theory?
- Defining a Galois Field based on primitive element versus polynomial?
- Can't find the relationship between two columns of numbers. Please Help
- Is computer science a branch of mathematics?
- Is there a bijection of $\mathbb{R}^n$ with itself such that the forward map is connected but the inverse is not?
- Identification of a quadrilateral as a trapezoid, rectangle, or square
- Generator of inertia group in function field extension
Popular # Hahtags
second-order-logic
numerical-methods
puzzle
logic
probability
number-theory
winding-number
real-analysis
integration
calculus
complex-analysis
sequences-and-series
proof-writing
set-theory
functions
homotopy-theory
elementary-number-theory
ordinary-differential-equations
circles
derivatives
game-theory
definite-integrals
elementary-set-theory
limits
multivariable-calculus
geometry
algebraic-number-theory
proof-verification
partial-derivative
algebra-precalculus
Popular Questions
- What is the integral of 1/x?
- How many squares actually ARE in this picture? Is this a trick question with no right answer?
- Is a matrix multiplied with its transpose something special?
- What is the difference between independent and mutually exclusive events?
- Visually stunning math concepts which are easy to explain
- taylor series of $\ln(1+x)$?
- How to tell if a set of vectors spans a space?
- Calculus question taking derivative to find horizontal tangent line
- How to determine if a function is one-to-one?
- Determine if vectors are linearly independent
- What does it mean to have a determinant equal to zero?
- Is this Batman equation for real?
- How to find perpendicular vector to another vector?
- How to find mean and median from histogram
- How many sides does a circle have?
These algorithms are based on linear algebra, multivariable calculus and probability theory (when the algorithms are stochastic). Specifically, rather than attempting to learn generic results from these branches, I would recommend starting with reviews of different optimisation algorithms, such as 1 or the more in-depth 2, and refer back to Khan-academy/Wikipedia if some of the mathematical formalisms are unclear.
Once you have gained an overview and intuition of a few basic algorithms, you should start reading the relevant literature on optimisation in deep learning, c.f. 3, 4 for reviews, and then the relevant references from these articles.