Gradient Descent Monotonically Decreases the Sharpness of Gradient Flow Solutions in Scalar Networks and Beyond von Kreisler, Itai, Nacson, Mor Shpigel, Soudry, Daniel, Carmon, Yair

Volltext bestellen

How Uniform Random Weights Induce Non-uniform Bias: Typical Interpolating Neural Networks Generalize with Narrow Teachers von Buzaglo, Gon, Harel, Itamar, Nacson, Mor Shpigel, Brutzkus, Alon, Srebro, Nathan, Soudry, Daniel

Volltext bestellen

DocVLM: Make Your VLM an Efficient Reader von Nacson, Mor Shpigel, Aberdam, Aviad, Ganz, Roy, Avraham, Elad Ben, Golts, Alona, Kittenplon, Yair, Mazor, Shai, Litman, Ron

Volltext bestellen

The Implicit Bias of Minima Stability in Multivariate Shallow ReLU Networks von Nacson, Mor Shpigel, Mulayoff, Rotem, Ongie, Greg, Michaeli, Tomer, Soudry, Daniel

Volltext bestellen

Stochastic Gradient Descent on Separable Data: Exact Convergence with a Fixed Learning Rate von Nacson, Mor Shpigel, Srebro, Nathan, Soudry, Daniel

Volltext bestellen

Stochastic Gradient Descent on Separable Data: Exact Convergence with a Fixed Learning Rate von Mor Shpigel Nacson, Srebro, Nathan, Soudry, Daniel

Volltext

At Stability's Edge: How to Adjust Hyperparameters to Preserve Minima Selection in Asynchronous Training of Neural Networks? von Giladi, Niv, Nacson, Mor Shpigel, Hoffer, Elad, Soudry, Daniel

Volltext bestellen

On the Implicit Bias of Initialization Shape: Beyond Infinitesimal Mirror Descent von Azulay, Shahar, Moroshko, Edward, Nacson, Mor Shpigel, Woodworth, Blake, Srebro, Nathan, Globerson, Amir, Soudry, Daniel

Volltext bestellen

Gradient Descent Monotonically Decreases the Sharpness of Gradient Flow Solutions in Scalar Networks and Beyond von Kreisler, Itai, Mor Shpigel Nacson, Soudry, Daniel, Carmon, Yair

Volltext

The Implicit Bias of Gradient Descent on Separable Data von Soudry, Daniel, Hoffer, Elad, Mor Shpigel Nacson, Gunasekar, Suriya, Srebro, Nathan

Volltext

ACTION RECOGNITION USING LIMITED DATA von Barzelay, Udi, Azulai, Ophir, Ben-Ari, Rami, Shpigel Nacson, Mor

Volltext bestellen

How Uniform Random Weights Induce Non-uniform Bias: Typical Interpolating Neural Networks Generalize with Narrow Teachers von Buzaglo, Gon, Harel, Itamar, Mor Shpigel Nacson, Brutzkus, Alon, Srebro, Nathan, Soudry, Daniel

Volltext

DocVLM: Make Your VLM an Efficient Reader von Mor Shpigel Nacson, Aberdam, Aviad, Ganz, Roy, Elad Ben Avraham, Golts, Alona, Kittenplon, Yair, Mazor, Shai, Litman, Ron

Volltext

The Implicit Bias of Minima Stability in Multivariate Shallow ReLU Networks von Mor Shpigel Nacson, Mulayoff, Rotem, Ongie, Greg, Michaeli, Tomer, Soudry, Daniel

Volltext

Lexicographic and Depth-Sensitive Margins in Homogeneous and Non-Homogeneous Deep Models von Nacson, Mor Shpigel, Gunasekar, Suriya, Lee, Jason D, Srebro, Nathan, Soudry, Daniel

Volltext bestellen

Convergence of Gradient Descent on Separable Data von Nacson, Mor Shpigel, Lee, Jason D, Gunasekar, Suriya, Savarese, Pedro H. P, Srebro, Nathan, Soudry, Daniel

Volltext bestellen

At Stability's Edge: How to Adjust Hyperparameters to Preserve Minima Selection in Asynchronous Training of Neural Networks? von Giladi, Niv, Mor Shpigel Nacson, Hoffer, Elad, Soudry, Daniel

Volltext

The Implicit Bias of Gradient Descent on Separable Data von Soudry, Daniel, Hoffer, Elad, Nacson, Mor Shpigel, Gunasekar, Suriya, Srebro, Nathan

Volltext bestellen

On the Implicit Bias of Initialization Shape: Beyond Infinitesimal Mirror Descent von Azulay, Shahar, Moroshko, Edward, Mor Shpigel Nacson, Woodworth, Blake, Srebro, Nathan, Globerson, Amir, Soudry, Daniel

Volltext

Lexicographic and Depth-Sensitive Margins in Homogeneous and Non-Homogeneous Deep Models von Mor Shpigel Nacson, Gunasekar, Suriya, Lee, Jason D, Srebro, Nathan, Soudry, Daniel

Volltext