GPT to learn some more ML optimisation / causal inference

What is numerical optimisation, How it is different from machine learning. List some usecases problems in numerical optimisation ?

Numerical optimization is the process of finding the values of input parameters that minimize or maximize a given objective function. It is different from machine learning in that it does not involve training a model with data, but instead relies on mathematical algorithms to find the best solution.

Some use cases of numerical optimization include:

• Portfolio optimization
• Supply chain optimization
• Vehicle routing
• Facility location
• Network design
• Scheduling
• Parameter estimation
• Image registration
• Model calibration
• Optimization of control systems

What are top 10  python packages for numerical optimization

• NumPy 
• SciPy 
• Scikit-Optimize 
• PyOpt 
• PyGMO 
• CVXOPT 
• Pulp 
• Pyomo 
• DEAP 
• Heuristic Optimization Algorithms (HOALib)

List some constraint for windmill turbine based on temperature, sunlight, humidity, windspeed with synthetic data python code pulp optimization solution

constraints = [

    # Temperature

    pulp.lpSum([temp_var[i] for i in range(len(temp_var))]) <= max_temp,

    pulp.lpSum([temp_var[i] for i in range(len(temp_var))]) >= min_temp,

    # Sunlight

    pulp.lpSum([sunlight_var[i] for i in range(len(sunlight_var))]) <= max_sunlight,

    pulp.lpSum([sunlight_var[i] for i in range(len(sunlight_var))]) >= min_sunlight,

    # Humidity

    pulp.lpSum([humidity_var[i] for i in range(len(humidity_var))]) <= max_humidity,

    pulp.lpSum([humidity_var[i] for i in range(len(humidity_var))]) >= min_humidity,

    # Windspeed

    pulp.lpSum([windspeed_var[i] for i in range(len(windspeed_var))]) <= max_windspeed,

    pulp.lpSum([windspeed_var[i] for i in range(len(windspeed_var))]) >= min_windspeed

]

List some usecases problems in operations research ?

• Vehicle Routing Problem
• Scheduling Problem
• Network Flow Problem
• Knapsack Problem
• Integer Programming Problem
• Queuing Theory Problem
•  Linear Programming Problem
•  Resource Allocation Problem
•  Facility Location Problem
•  Project Scheduling Problem

List some usecases problems in causal inference ?

• Estimating the effect of a treatment on an outcome of interest
• Estimating the effect of a policy change on a population
• Estimating the effect of a marketing campaign on sales
• Estimating the effect of a new product on customer retention
• Estimating the effect of a change in pricing on customer demand
• Estimating the effect of a change in customer service on customer satisfaction
• Estimating the effect of a change in advertising on brand awareness
• Estimating the effect of a change in the labor market on wages
• Estimating the effect of a change in government regulations on economic growth
• Estimating the effect of a change in the environment on public health

What is casual inference in layman terms

Casual inference is a type of reasoning that allows us to draw conclusions based on our observations. In layman's terms, it is the process of making assumptions or guesses about something based on what we know or have seen. For example, if you see someone walking down the street wearing a suit and carrying a briefcase, you can infer that they are likely on their way to work.

List some usecases problems in Bayesian modelling ?

• Estimating the probability of a medical diagnosis given a set of symptoms.
• Predicting the probability of a customer purchasing a product given their browsing history.
• Estimating the probability of a machine failure given a set of sensor readings.
• Predicting the probability of a customer defaulting on a loan given their financial history.
• Estimating the probability of a terrorist attack given a set of intelligence data.
• Predicting the probability of a stock price movement given market data.
• Estimating the probability of a natural disaster given weather patterns.
• Predicting the probability of a customer churning given their usage data.

What is difference between causal interference vs AB testing

Causal inference is a method of determining the cause-and-effect relationship between two variables. It is used to identify the cause of a particular outcome. It is based on the assumption that there is a causal relationship between the two variables.

AB testing is a method of comparing two versions of a product or service to determine which one performs better. It is used to determine which version of a product or service is more effective. It is based on the assumption that the two versions are statistically different.

List some usecases problems in differentiable programming ?

• Optimizing hyperparameters in neural networks
• Automatically generating neural network architectures
• Automatically generating code from a given specification
• Automatically tuning the parameters of a given model
• Automatically generating data pre-processing pipelines
• Automatically generating feature engineering pipelines
• Automatically generating loss functions
• Automatically generating optimization algorithms
• Automatically generating regularization techniques
• Automatically generating distributed training strategies

Bayesian modeling is generative probability based on historical data, Is it correct ?

Yes, that is correct. Bayesian modeling is a type of generative probability model that uses historical data to make predictions about future events.

When can we use differentiable programming , Does it have advantage over deep learning

Differentiable programming can be used when a problem requires the use of a combination of symbolic and numerical computation. It has the advantage of being able to combine the flexibility of symbolic computation with the power of deep learning. This allows for more complex models to be created and trained, which can lead to better results. Additionally, differentiable programming can be used to create models that are more interpretable and easier to debug.

Keep Exploring!!!